From 57a49018b10fb9d1c290d82a4fa367539185f509 Mon Sep 17 00:00:00 2001 From: cyy Date: Sun, 3 Nov 2024 20:40:47 +0000 Subject: [PATCH] [5/N] Fix Wextra-semi warning (#139465) Fixes #ISSUE_NUMBER Pull Request resolved: https://github.com/pytorch/pytorch/pull/139465 Approved by: https://github.com/ezyang --- aten/src/ATen/ParallelThreadPoolNative.cpp | 2 +- .../src/ATen/cpu/vec/vec256/vec256_bfloat16.h | 4 +- .../src/ATen/cpu/vec/vec512/vec512_bfloat16.h | 4 +- .../impl/HIPGuardImplMasqueradingAsCUDA.cpp | 2 +- aten/src/ATen/mps/MPSAllocatorInterface.h | 2 +- aten/src/ATen/mps/MPSGuardImpl.h | 2 +- .../ATen/native/BatchLinearAlgebraKernel.cpp | 180 +++++++++--------- aten/src/ATen/native/QuantizedLinear.cpp | 2 +- aten/src/ATen/native/cpu/Activation.cpp | 34 ++-- aten/src/ATen/native/cpu/BinaryOpsKernel.cpp | 24 +-- aten/src/ATen/native/cpu/ComplexKernel.cpp | 2 +- .../ATen/native/cpu/DepthwiseConvKernel.cpp | 2 +- .../ATen/native/cpu/FlashAttentionKernel.cpp | 4 +- aten/src/ATen/native/cpu/PowKernel.cpp | 4 +- aten/src/ATen/native/cpu/SoftMaxKernel.cpp | 10 +- aten/src/ATen/native/cpu/UnaryOpsKernel.cpp | 18 +- aten/src/ATen/native/cpu/int4mm_kernel.cpp | 4 +- aten/src/ATen/native/cpu/int8mm_kernel.cpp | 2 +- aten/src/ATen/native/cuda/AbsKernel.cu | 2 +- .../ATen/native/cuda/ActivationEluKernel.cu | 4 +- .../ATen/native/cuda/ActivationGluKernel.cu | 4 +- .../native/cuda/ActivationHardshrinkKernel.cu | 2 +- .../cuda/ActivationHardsigmoidKernel.cu | 4 +- .../native/cuda/ActivationHardswishKernel.cu | 4 +- .../native/cuda/ActivationHardtanhKernel.cu | 2 +- .../native/cuda/ActivationLeakyReluKernel.cu | 4 +- .../native/cuda/ActivationLogSigmoidKernel.cu | 2 +- .../ATen/native/cuda/ActivationMishKernel.cu | 4 +- .../ATen/native/cuda/ActivationPreluKernel.cu | 4 +- .../ATen/native/cuda/ActivationSiluKernel.cu | 4 +- .../native/cuda/ActivationSoftplusKernel.cu | 4 +- .../native/cuda/ActivationSoftshrinkKernel.cu | 4 +- .../native/cuda/ActivationThresholdKernel.cu | 2 +- .../native/cuda/BinaryBitwiseOpsKernels.cu | 6 +- .../ATen/native/cuda/BinaryDivFloorKernel.cu | 2 +- .../ATen/native/cuda/BinaryDivTrueKernel.cu | 2 +- .../ATen/native/cuda/BinaryDivTruncKernel.cu | 2 +- .../native/cuda/BinaryGeometricKernels.cu | 4 +- .../native/cuda/BinaryLogicalOpsKernels.cu | 6 +- .../cuda/BinaryMiscBackwardOpsKernels.cu | 6 +- .../ATen/native/cuda/BinaryMiscOpsKernels.cu | 10 +- aten/src/ATen/native/cuda/BinaryMulKernel.cu | 2 +- .../ATen/native/cuda/BinaryRemainderKernel.cu | 4 +- .../ATen/native/cuda/BinaryShiftOpsKernels.cu | 4 +- aten/src/ATen/native/cuda/CompareEQKernel.cu | 4 +- aten/src/ATen/native/cuda/CompareKernels.cu | 8 +- aten/src/ATen/native/cuda/ComplexKernel.cu | 4 +- aten/src/ATen/native/cuda/Copy.cu | 2 +- aten/src/ATen/native/cuda/CopysignKernel.cu | 2 +- aten/src/ATen/native/cuda/CrossKernel.cu | 2 +- aten/src/ATen/native/cuda/DistanceKernel.cu | 8 +- .../ATen/native/cuda/DistributionBernoulli.cu | 4 +- .../native/cuda/DistributionCauchyKernel.cu | 2 +- .../cuda/DistributionExponentialKernel.cu | 2 +- .../cuda/DistributionGeometricKernel.cu | 2 +- .../cuda/DistributionLogNormalKernel.cu | 2 +- .../ATen/native/cuda/DistributionNormal.cu | 2 +- .../native/cuda/DistributionRandomKernel.cu | 6 +- .../ATen/native/cuda/DistributionUniform.cu | 2 +- aten/src/ATen/native/cuda/FillKernel.cu | 2 +- .../cuda/FunctionOfAMatrixUtilsKernel.cu | 2 +- aten/src/ATen/native/cuda/GcdLcmKernel.cu | 4 +- aten/src/ATen/native/cuda/IGammaKernel.cu | 4 +- aten/src/ATen/native/cuda/IndexKernel.cu | 14 +- aten/src/ATen/native/cuda/Lerp.cu | 4 +- aten/src/ATen/native/cuda/LinearAlgebra.cu | 4 +- aten/src/ATen/native/cuda/LogAddExpKernel.cu | 4 +- .../native/cuda/MaxMinElementwiseKernel.cu | 8 +- .../ATen/native/cuda/PointwiseOpsKernel.cu | 10 +- aten/src/ATen/native/cuda/PowKernel.cu | 4 +- .../ATen/native/cuda/ReduceArgMaxKernel.cu | 2 +- .../ATen/native/cuda/ReduceArgMinKernel.cu | 2 +- .../src/ATen/native/cuda/ReduceLogicKernel.cu | 4 +- .../ATen/native/cuda/ReduceMaxValuesKernel.cu | 2 +- .../ATen/native/cuda/ReduceMinValuesKernel.cu | 2 +- .../ATen/native/cuda/ReduceMomentKernel.cu | 4 +- .../ATen/native/cuda/ReduceSumProdKernel.cu | 6 +- aten/src/ATen/native/cuda/RenormKernel.cu | 2 +- .../ATen/native/cuda/ScatterGatherKernel.cu | 14 +- aten/src/ATen/native/cuda/SegmentReduce.cu | 4 +- aten/src/ATen/native/cuda/SpectralOps.cu | 2 +- aten/src/ATen/native/cuda/StepKernel.cu | 4 +- aten/src/ATen/native/cuda/TensorCompare.cu | 14 +- .../ATen/native/cuda/UnaryComplexKernels.cu | 4 +- .../ATen/native/cuda/UnaryFractionKernels.cu | 14 +- .../src/ATen/native/cuda/UnaryGammaKernels.cu | 6 +- .../native/cuda/UnaryGeometricAcosKernel.cu | 2 +- .../native/cuda/UnaryGeometricAcoshKernel.cu | 2 +- .../native/cuda/UnaryGeometricAsinKernel.cu | 2 +- .../native/cuda/UnaryGeometricAsinhKernel.cu | 2 +- .../native/cuda/UnaryGeometricAtanKernel.cu | 2 +- .../native/cuda/UnaryGeometricAtanhKernel.cu | 2 +- .../native/cuda/UnaryGeometricCosKernel.cu | 2 +- .../native/cuda/UnaryGeometricCoshKernel.cu | 2 +- .../native/cuda/UnaryGeometricSinKernel.cu | 2 +- .../native/cuda/UnaryGeometricSinhKernel.cu | 2 +- .../native/cuda/UnaryGeometricTanKernel.cu | 2 +- .../native/cuda/UnaryGeometricTanhKernel.cu | 2 +- aten/src/ATen/native/cuda/UnaryLogKernels.cu | 8 +- aten/src/ATen/native/cuda/UnaryOpsKernel.cu | 14 +- aten/src/ATen/native/cuda/UnarySignKernels.cu | 10 +- .../ATen/native/cuda/UnarySpecialOpsKernel.cu | 32 ++-- .../ATen/native/cuda/UnfoldBackwardKernel.cu | 2 +- aten/src/ATen/native/cuda/ZetaKernel.cu | 2 +- aten/src/ATen/native/cuda/airy_ai.cu | 2 +- aten/src/ATen/native/cuda/bessel_j0.cu | 2 +- aten/src/ATen/native/cuda/bessel_j1.cu | 2 +- aten/src/ATen/native/cuda/bessel_y0.cu | 2 +- aten/src/ATen/native/cuda/bessel_y1.cu | 2 +- .../native/cuda/chebyshev_polynomial_t.cu | 2 +- .../native/cuda/chebyshev_polynomial_u.cu | 2 +- .../native/cuda/chebyshev_polynomial_v.cu | 2 +- .../native/cuda/chebyshev_polynomial_w.cu | 2 +- .../src/ATen/native/cuda/group_norm_kernel.cu | 4 +- .../ATen/native/cuda/hermite_polynomial_h.cu | 2 +- .../ATen/native/cuda/hermite_polynomial_he.cu | 2 +- .../ATen/native/cuda/laguerre_polynomial_l.cu | 2 +- .../src/ATen/native/cuda/layer_norm_kernel.cu | 4 +- .../ATen/native/cuda/legendre_polynomial_p.cu | 2 +- .../ATen/native/cuda/modified_bessel_i0.cu | 2 +- .../ATen/native/cuda/modified_bessel_i1.cu | 2 +- .../ATen/native/cuda/modified_bessel_k0.cu | 2 +- .../ATen/native/cuda/modified_bessel_k1.cu | 2 +- .../native/cuda/scaled_modified_bessel_k0.cu | 2 +- .../native/cuda/scaled_modified_bessel_k1.cu | 2 +- .../cuda/shifted_chebyshev_polynomial_t.cu | 2 +- .../cuda/shifted_chebyshev_polynomial_u.cu | 2 +- .../cuda/shifted_chebyshev_polynomial_v.cu | 2 +- .../cuda/shifted_chebyshev_polynomial_w.cu | 2 +- .../ATen/native/cuda/spherical_bessel_j0.cu | 2 +- aten/src/ATen/native/metal/MetalGuardImpl.cpp | 2 +- .../native/mps/operations/BinaryKernel.mm | 8 +- .../ATen/native/mps/operations/CrossKernel.mm | 2 +- .../native/mps/operations/HistogramKernel.mm | 6 +- .../ATen/native/mps/operations/Indexing.mm | 4 +- .../ATen/native/mps/operations/SpecialOps.mm | 2 +- .../native/mps/operations/TensorCompare.mm | 6 +- .../cpu/kernels/QuantizedOpKernels.cpp | 4 +- .../ATen/native/vulkan/VulkanGuardImpl.cpp | 2 +- 139 files changed, 391 insertions(+), 391 deletions(-) diff --git a/aten/src/ATen/ParallelThreadPoolNative.cpp b/aten/src/ATen/ParallelThreadPoolNative.cpp index 75dd56c263e..5af4dfcce08 100644 --- a/aten/src/ATen/ParallelThreadPoolNative.cpp +++ b/aten/src/ATen/ParallelThreadPoolNative.cpp @@ -45,7 +45,7 @@ std::shared_ptr create_c10_threadpool( } // namespace -C10_REGISTER_CREATOR(ThreadPoolRegistry, C10, create_c10_threadpool); +C10_REGISTER_CREATOR(ThreadPoolRegistry, C10, create_c10_threadpool) void set_num_interop_threads(int nthreads) { TORCH_CHECK(nthreads > 0, "Expected positive number of threads"); diff --git a/aten/src/ATen/cpu/vec/vec256/vec256_bfloat16.h b/aten/src/ATen/cpu/vec/vec256/vec256_bfloat16.h index 9402f1dd404..60d9965d983 100644 --- a/aten/src/ATen/cpu/vec/vec256/vec256_bfloat16.h +++ b/aten/src/ATen/cpu/vec/vec256/vec256_bfloat16.h @@ -1119,8 +1119,8 @@ inline void load_fp32_from_##name(const type *data, Vectorized& out1, Vec out1 = out1_values; \ out2 = out2_values; \ } -LOAD_FP32_VECTORIZED_INIT(BFloat16, bf16); -LOAD_FP32_VECTORIZED_INIT(Half, fp16); +LOAD_FP32_VECTORIZED_INIT(BFloat16, bf16) +LOAD_FP32_VECTORIZED_INIT(Half, fp16) #else // defined(CPU_CAPABILITY_AVX2) #define LOAD_FP32_NON_VECTORIZED_INIT(type, name) \ diff --git a/aten/src/ATen/cpu/vec/vec512/vec512_bfloat16.h b/aten/src/ATen/cpu/vec/vec512/vec512_bfloat16.h index ba6e1c2a4d1..843543c2f7c 100644 --- a/aten/src/ATen/cpu/vec/vec512/vec512_bfloat16.h +++ b/aten/src/ATen/cpu/vec/vec512/vec512_bfloat16.h @@ -1707,8 +1707,8 @@ inline void load_fp32_from_##name(const type *data, Vectorized& out1, Vec out1 = out1_values; \ out2 = out2_values; \ } -LOAD_FP32_VECTORIZED_INIT(BFloat16, bf16); -LOAD_FP32_VECTORIZED_INIT(Half, fp16); +LOAD_FP32_VECTORIZED_INIT(BFloat16, bf16) +LOAD_FP32_VECTORIZED_INIT(Half, fp16) #else // defined(CPU_CAPABILITY_AVX512) #define LOAD_FP32_NON_VECTORIZED_INIT(type, name) \ diff --git a/aten/src/ATen/hip/impl/HIPGuardImplMasqueradingAsCUDA.cpp b/aten/src/ATen/hip/impl/HIPGuardImplMasqueradingAsCUDA.cpp index 2215f5587e8..3b05432d5c8 100644 --- a/aten/src/ATen/hip/impl/HIPGuardImplMasqueradingAsCUDA.cpp +++ b/aten/src/ATen/hip/impl/HIPGuardImplMasqueradingAsCUDA.cpp @@ -11,4 +11,4 @@ // // This hack can be removed once PyTorch is out-of-place HIPified, and // doesn't pretend CUDA is HIP. -C10_REGISTER_GUARD_IMPL(CUDA, at::cuda::HIPGuardImplMasqueradingAsCUDA); +C10_REGISTER_GUARD_IMPL(CUDA, at::cuda::HIPGuardImplMasqueradingAsCUDA) diff --git a/aten/src/ATen/mps/MPSAllocatorInterface.h b/aten/src/ATen/mps/MPSAllocatorInterface.h index 9aa4769f76e..b602d692a09 100644 --- a/aten/src/ATen/mps/MPSAllocatorInterface.h +++ b/aten/src/ATen/mps/MPSAllocatorInterface.h @@ -55,7 +55,7 @@ class IMpsAllocatorCallback { // MPS allocator will execute every registered callback when a block of memory is freed. C10_DECLARE_REGISTRY(MPSAllocatorCallbacksRegistry, IMpsAllocatorCallback); #define REGISTER_MPS_ALLOCATOR_CALLBACK(name, ...) \ - C10_REGISTER_CLASS(MPSAllocatorCallbacksRegistry, name, __VA_ARGS__); + C10_REGISTER_CLASS(MPSAllocatorCallbacksRegistry, name, __VA_ARGS__) IMPSAllocator* getIMPSAllocator(bool sharedAllocator = false); diff --git a/aten/src/ATen/mps/MPSGuardImpl.h b/aten/src/ATen/mps/MPSGuardImpl.h index 6132cd8055e..23cb00742c3 100644 --- a/aten/src/ATen/mps/MPSGuardImpl.h +++ b/aten/src/ATen/mps/MPSGuardImpl.h @@ -176,6 +176,6 @@ struct OptionalMPSGuard { }; -C10_REGISTER_GUARD_IMPL(MPS, MPSGuardImpl); +C10_REGISTER_GUARD_IMPL(MPS, MPSGuardImpl) } // namespace at::mps diff --git a/aten/src/ATen/native/BatchLinearAlgebraKernel.cpp b/aten/src/ATen/native/BatchLinearAlgebraKernel.cpp index ab1dd139b1b..76f7f2b3c6b 100644 --- a/aten/src/ATen/native/BatchLinearAlgebraKernel.cpp +++ b/aten/src/ATen/native/BatchLinearAlgebraKernel.cpp @@ -1135,108 +1135,108 @@ void unpack_pivots_cpu_kernel(TensorIterator& iter, const int64_t dim_size, cons } } // anonymous namespace -REGISTER_ARCH_DISPATCH(cholesky_stub, DEFAULT, &cholesky_kernel); -REGISTER_AVX512_DISPATCH(cholesky_stub, &cholesky_kernel); -REGISTER_AVX2_DISPATCH(cholesky_stub, &cholesky_kernel); -REGISTER_VSX_DISPATCH(cholesky_stub, &cholesky_kernel); -REGISTER_ZVECTOR_DISPATCH(cholesky_stub, &cholesky_kernel); -REGISTER_SVE256_DISPATCH(cholesky_stub, &cholesky_kernel); +REGISTER_ARCH_DISPATCH(cholesky_stub, DEFAULT, &cholesky_kernel) +REGISTER_AVX512_DISPATCH(cholesky_stub, &cholesky_kernel) +REGISTER_AVX2_DISPATCH(cholesky_stub, &cholesky_kernel) +REGISTER_VSX_DISPATCH(cholesky_stub, &cholesky_kernel) +REGISTER_ZVECTOR_DISPATCH(cholesky_stub, &cholesky_kernel) +REGISTER_SVE256_DISPATCH(cholesky_stub, &cholesky_kernel) -REGISTER_ARCH_DISPATCH(cholesky_inverse_stub, DEFAULT, &cholesky_inverse_kernel_impl); -REGISTER_AVX512_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl); -REGISTER_AVX2_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl); -REGISTER_VSX_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl); -REGISTER_ZVECTOR_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl); -REGISTER_SVE256_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl); +REGISTER_ARCH_DISPATCH(cholesky_inverse_stub, DEFAULT, &cholesky_inverse_kernel_impl) +REGISTER_AVX512_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl) +REGISTER_AVX2_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl) +REGISTER_VSX_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl) +REGISTER_ZVECTOR_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl) +REGISTER_SVE256_DISPATCH(cholesky_inverse_stub, &cholesky_inverse_kernel_impl) -REGISTER_ARCH_DISPATCH(linalg_eig_stub, DEFAULT, &linalg_eig_kernel); -REGISTER_AVX512_DISPATCH(linalg_eig_stub, &linalg_eig_kernel); -REGISTER_AVX2_DISPATCH(linalg_eig_stub, &linalg_eig_kernel); -REGISTER_VSX_DISPATCH(linalg_eig_stub, &linalg_eig_kernel); -REGISTER_ZVECTOR_DISPATCH(linalg_eig_stub, &linalg_eig_kernel); -REGISTER_SVE256_DISPATCH(linalg_eig_stub, &linalg_eig_kernel); +REGISTER_ARCH_DISPATCH(linalg_eig_stub, DEFAULT, &linalg_eig_kernel) +REGISTER_AVX512_DISPATCH(linalg_eig_stub, &linalg_eig_kernel) +REGISTER_AVX2_DISPATCH(linalg_eig_stub, &linalg_eig_kernel) +REGISTER_VSX_DISPATCH(linalg_eig_stub, &linalg_eig_kernel) +REGISTER_ZVECTOR_DISPATCH(linalg_eig_stub, &linalg_eig_kernel) +REGISTER_SVE256_DISPATCH(linalg_eig_stub, &linalg_eig_kernel) -REGISTER_ARCH_DISPATCH(linalg_eigh_stub, DEFAULT, &linalg_eigh_kernel); -REGISTER_AVX512_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel); -REGISTER_AVX2_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel); -REGISTER_VSX_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel); -REGISTER_ZVECTOR_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel); -REGISTER_SVE256_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel); +REGISTER_ARCH_DISPATCH(linalg_eigh_stub, DEFAULT, &linalg_eigh_kernel) +REGISTER_AVX512_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel) +REGISTER_AVX2_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel) +REGISTER_VSX_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel) +REGISTER_ZVECTOR_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel) +REGISTER_SVE256_DISPATCH(linalg_eigh_stub, &linalg_eigh_kernel) -REGISTER_ARCH_DISPATCH(geqrf_stub, DEFAULT, &geqrf_kernel); -REGISTER_AVX512_DISPATCH(geqrf_stub, &geqrf_kernel); -REGISTER_AVX2_DISPATCH(geqrf_stub, &geqrf_kernel); -REGISTER_VSX_DISPATCH(geqrf_stub, &geqrf_kernel); -REGISTER_ZVECTOR_DISPATCH(geqrf_stub, &geqrf_kernel); -REGISTER_SVE256_DISPATCH(geqrf_stub, &geqrf_kernel); +REGISTER_ARCH_DISPATCH(geqrf_stub, DEFAULT, &geqrf_kernel) +REGISTER_AVX512_DISPATCH(geqrf_stub, &geqrf_kernel) +REGISTER_AVX2_DISPATCH(geqrf_stub, &geqrf_kernel) +REGISTER_VSX_DISPATCH(geqrf_stub, &geqrf_kernel) +REGISTER_ZVECTOR_DISPATCH(geqrf_stub, &geqrf_kernel) +REGISTER_SVE256_DISPATCH(geqrf_stub, &geqrf_kernel) -REGISTER_ARCH_DISPATCH(orgqr_stub, DEFAULT, &orgqr_kernel_impl); -REGISTER_AVX512_DISPATCH(orgqr_stub, &orgqr_kernel_impl); -REGISTER_AVX2_DISPATCH(orgqr_stub, &orgqr_kernel_impl); -REGISTER_VSX_DISPATCH(orgqr_stub, &orgqr_kernel_impl); -REGISTER_ZVECTOR_DISPATCH(orgqr_stub, &orgqr_kernel_impl); -REGISTER_SVE256_DISPATCH(orgqr_stub, &orgqr_kernel_impl); +REGISTER_ARCH_DISPATCH(orgqr_stub, DEFAULT, &orgqr_kernel_impl) +REGISTER_AVX512_DISPATCH(orgqr_stub, &orgqr_kernel_impl) +REGISTER_AVX2_DISPATCH(orgqr_stub, &orgqr_kernel_impl) +REGISTER_VSX_DISPATCH(orgqr_stub, &orgqr_kernel_impl) +REGISTER_ZVECTOR_DISPATCH(orgqr_stub, &orgqr_kernel_impl) +REGISTER_SVE256_DISPATCH(orgqr_stub, &orgqr_kernel_impl) -REGISTER_ARCH_DISPATCH(ormqr_stub, DEFAULT, &ormqr_kernel); -REGISTER_AVX512_DISPATCH(ormqr_stub, &ormqr_kernel); -REGISTER_AVX2_DISPATCH(ormqr_stub, &ormqr_kernel); -REGISTER_VSX_DISPATCH(ormqr_stub, &ormqr_kernel); -REGISTER_ZVECTOR_DISPATCH(ormqr_stub, &ormqr_kernel); -REGISTER_SVE256_DISPATCH(ormqr_stub, &ormqr_kernel); +REGISTER_ARCH_DISPATCH(ormqr_stub, DEFAULT, &ormqr_kernel) +REGISTER_AVX512_DISPATCH(ormqr_stub, &ormqr_kernel) +REGISTER_AVX2_DISPATCH(ormqr_stub, &ormqr_kernel) +REGISTER_VSX_DISPATCH(ormqr_stub, &ormqr_kernel) +REGISTER_ZVECTOR_DISPATCH(ormqr_stub, &ormqr_kernel) +REGISTER_SVE256_DISPATCH(ormqr_stub, &ormqr_kernel) -REGISTER_ARCH_DISPATCH(lstsq_stub, DEFAULT, &lstsq_kernel); -REGISTER_AVX512_DISPATCH(lstsq_stub, &lstsq_kernel); -REGISTER_AVX2_DISPATCH(lstsq_stub, &lstsq_kernel); -REGISTER_VSX_DISPATCH(lstsq_stub, &lstsq_kernel); -REGISTER_ZVECTOR_DISPATCH(lstsq_stub, &lstsq_kernel); -REGISTER_SVE256_DISPATCH(lstsq_stub, &lstsq_kernel); +REGISTER_ARCH_DISPATCH(lstsq_stub, DEFAULT, &lstsq_kernel) +REGISTER_AVX512_DISPATCH(lstsq_stub, &lstsq_kernel) +REGISTER_AVX2_DISPATCH(lstsq_stub, &lstsq_kernel) +REGISTER_VSX_DISPATCH(lstsq_stub, &lstsq_kernel) +REGISTER_ZVECTOR_DISPATCH(lstsq_stub, &lstsq_kernel) +REGISTER_SVE256_DISPATCH(lstsq_stub, &lstsq_kernel) -REGISTER_ARCH_DISPATCH(triangular_solve_stub, DEFAULT, &triangular_solve_kernel); -REGISTER_AVX512_DISPATCH(triangular_solve_stub, &triangular_solve_kernel); -REGISTER_AVX2_DISPATCH(triangular_solve_stub, &triangular_solve_kernel); -REGISTER_VSX_DISPATCH(triangular_solve_stub, &triangular_solve_kernel); -REGISTER_ZVECTOR_DISPATCH(triangular_solve_stub, &triangular_solve_kernel); -REGISTER_SVE256_DISPATCH(triangular_solve_stub, &triangular_solve_kernel); +REGISTER_ARCH_DISPATCH(triangular_solve_stub, DEFAULT, &triangular_solve_kernel) +REGISTER_AVX512_DISPATCH(triangular_solve_stub, &triangular_solve_kernel) +REGISTER_AVX2_DISPATCH(triangular_solve_stub, &triangular_solve_kernel) +REGISTER_VSX_DISPATCH(triangular_solve_stub, &triangular_solve_kernel) +REGISTER_ZVECTOR_DISPATCH(triangular_solve_stub, &triangular_solve_kernel) +REGISTER_SVE256_DISPATCH(triangular_solve_stub, &triangular_solve_kernel) -REGISTER_ARCH_DISPATCH(lu_factor_stub, DEFAULT, &lu_factor_kernel); -REGISTER_AVX512_DISPATCH(lu_factor_stub, &lu_factor_kernel); -REGISTER_AVX2_DISPATCH(lu_factor_stub, &lu_factor_kernel); -REGISTER_VSX_DISPATCH(lu_factor_stub, &lu_factor_kernel); -REGISTER_ZVECTOR_DISPATCH(lu_factor_stub, &lu_factor_kernel); -REGISTER_SVE256_DISPATCH(lu_factor_stub, &lu_factor_kernel); +REGISTER_ARCH_DISPATCH(lu_factor_stub, DEFAULT, &lu_factor_kernel) +REGISTER_AVX512_DISPATCH(lu_factor_stub, &lu_factor_kernel) +REGISTER_AVX2_DISPATCH(lu_factor_stub, &lu_factor_kernel) +REGISTER_VSX_DISPATCH(lu_factor_stub, &lu_factor_kernel) +REGISTER_ZVECTOR_DISPATCH(lu_factor_stub, &lu_factor_kernel) +REGISTER_SVE256_DISPATCH(lu_factor_stub, &lu_factor_kernel) -REGISTER_ARCH_DISPATCH(ldl_factor_stub, DEFAULT, &ldl_factor_kernel); -REGISTER_AVX512_DISPATCH(ldl_factor_stub, &ldl_factor_kernel); -REGISTER_AVX2_DISPATCH(ldl_factor_stub, &ldl_factor_kernel); -REGISTER_VSX_DISPATCH(ldl_factor_stub, &ldl_factor_kernel); -REGISTER_ZVECTOR_DISPATCH(ldl_factor_stub, &ldl_factor_kernel); -REGISTER_SVE256_DISPATCH(ldl_factor_stub, &ldl_factor_kernel); +REGISTER_ARCH_DISPATCH(ldl_factor_stub, DEFAULT, &ldl_factor_kernel) +REGISTER_AVX512_DISPATCH(ldl_factor_stub, &ldl_factor_kernel) +REGISTER_AVX2_DISPATCH(ldl_factor_stub, &ldl_factor_kernel) +REGISTER_VSX_DISPATCH(ldl_factor_stub, &ldl_factor_kernel) +REGISTER_ZVECTOR_DISPATCH(ldl_factor_stub, &ldl_factor_kernel) +REGISTER_SVE256_DISPATCH(ldl_factor_stub, &ldl_factor_kernel) -REGISTER_ARCH_DISPATCH(ldl_solve_stub, DEFAULT, &ldl_solve_kernel); -REGISTER_AVX512_DISPATCH(ldl_solve_stub, &ldl_solve_kernel); -REGISTER_AVX2_DISPATCH(ldl_solve_stub, &ldl_solve_kernel); -REGISTER_VSX_DISPATCH(ldl_solve_stub, &ldl_solve_kernel); -REGISTER_ZVECTOR_DISPATCH(ldl_solve_stub, &ldl_solve_kernel); -REGISTER_SVE256_DISPATCH(ldl_solve_stub, &ldl_solve_kernel); +REGISTER_ARCH_DISPATCH(ldl_solve_stub, DEFAULT, &ldl_solve_kernel) +REGISTER_AVX512_DISPATCH(ldl_solve_stub, &ldl_solve_kernel) +REGISTER_AVX2_DISPATCH(ldl_solve_stub, &ldl_solve_kernel) +REGISTER_VSX_DISPATCH(ldl_solve_stub, &ldl_solve_kernel) +REGISTER_ZVECTOR_DISPATCH(ldl_solve_stub, &ldl_solve_kernel) +REGISTER_SVE256_DISPATCH(ldl_solve_stub, &ldl_solve_kernel) -REGISTER_ARCH_DISPATCH(lu_solve_stub, DEFAULT, &lu_solve_kernel); -REGISTER_AVX512_DISPATCH(lu_solve_stub, &lu_solve_kernel); -REGISTER_AVX2_DISPATCH(lu_solve_stub, &lu_solve_kernel); -REGISTER_VSX_DISPATCH(lu_solve_stub, &lu_solve_kernel); -REGISTER_ZVECTOR_DISPATCH(lu_solve_stub, &lu_solve_kernel); -REGISTER_SVE256_DISPATCH(lu_solve_stub, &lu_solve_kernel); +REGISTER_ARCH_DISPATCH(lu_solve_stub, DEFAULT, &lu_solve_kernel) +REGISTER_AVX512_DISPATCH(lu_solve_stub, &lu_solve_kernel) +REGISTER_AVX2_DISPATCH(lu_solve_stub, &lu_solve_kernel) +REGISTER_VSX_DISPATCH(lu_solve_stub, &lu_solve_kernel) +REGISTER_ZVECTOR_DISPATCH(lu_solve_stub, &lu_solve_kernel) +REGISTER_SVE256_DISPATCH(lu_solve_stub, &lu_solve_kernel) -REGISTER_ARCH_DISPATCH(svd_stub, DEFAULT, &svd_kernel); -REGISTER_AVX512_DISPATCH(svd_stub, &svd_kernel); -REGISTER_AVX2_DISPATCH(svd_stub, &svd_kernel); -REGISTER_VSX_DISPATCH(svd_stub, &svd_kernel); -REGISTER_ZVECTOR_DISPATCH(svd_stub, &svd_kernel); -REGISTER_SVE256_DISPATCH(svd_stub, &svd_kernel); +REGISTER_ARCH_DISPATCH(svd_stub, DEFAULT, &svd_kernel) +REGISTER_AVX512_DISPATCH(svd_stub, &svd_kernel) +REGISTER_AVX2_DISPATCH(svd_stub, &svd_kernel) +REGISTER_VSX_DISPATCH(svd_stub, &svd_kernel) +REGISTER_ZVECTOR_DISPATCH(svd_stub, &svd_kernel) +REGISTER_SVE256_DISPATCH(svd_stub, &svd_kernel) -REGISTER_ARCH_DISPATCH(unpack_pivots_stub, DEFAULT, &unpack_pivots_cpu_kernel); -REGISTER_AVX512_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel); -REGISTER_AVX2_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel); -REGISTER_VSX_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel); -REGISTER_ZVECTOR_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel); -REGISTER_SVE256_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel); +REGISTER_ARCH_DISPATCH(unpack_pivots_stub, DEFAULT, &unpack_pivots_cpu_kernel) +REGISTER_AVX512_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel) +REGISTER_AVX2_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel) +REGISTER_VSX_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel) +REGISTER_ZVECTOR_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel) +REGISTER_SVE256_DISPATCH(unpack_pivots_stub, &unpack_pivots_cpu_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/QuantizedLinear.cpp b/aten/src/ATen/native/QuantizedLinear.cpp index ce83f6b9244..c4f2ea0fd0b 100644 --- a/aten/src/ATen/native/QuantizedLinear.cpp +++ b/aten/src/ATen/native/QuantizedLinear.cpp @@ -32,7 +32,7 @@ #endif // USE_FBGEMM namespace caffe2 { -CAFFE_KNOWN_TYPE(c10::intrusive_ptr); +CAFFE_KNOWN_TYPE(c10::intrusive_ptr) } // namespace caffe2 #ifdef USE_FBGEMM diff --git a/aten/src/ATen/native/cpu/Activation.cpp b/aten/src/ATen/native/cpu/Activation.cpp index 8af56f2da12..589cf213681 100644 --- a/aten/src/ATen/native/cpu/Activation.cpp +++ b/aten/src/ATen/native/cpu/Activation.cpp @@ -1412,22 +1412,22 @@ REGISTER_DISPATCH(hardshrink_stub, &hardshrink_kernel) REGISTER_DISPATCH(softshrink_stub, &softshrink_kernel) REGISTER_DISPATCH(shrink_backward_stub, &shrink_backward_kernel) -ALSO_REGISTER_AVX512_DISPATCH(log_sigmoid_cpu_stub, &log_sigmoid_cpu_kernel); -ALSO_REGISTER_AVX512_DISPATCH(log_sigmoid_backward_stub, &log_sigmoid_backward_cpu_kernel); -ALSO_REGISTER_AVX512_DISPATCH(glu_stub, &glu_kernel); -ALSO_REGISTER_AVX512_DISPATCH(glu_backward_stub, &glu_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(glu_jvp_stub, &glu_jvp_kernel); -ALSO_REGISTER_AVX512_DISPATCH(elu_stub, &elu_kernel); -ALSO_REGISTER_AVX512_DISPATCH(elu_backward_stub, &elu_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(GeluKernel, &GeluKernelImpl); -ALSO_REGISTER_AVX512_DISPATCH(GeluBackwardKernel, &GeluBackwardKernelImpl); -ALSO_REGISTER_AVX512_DISPATCH(hardswish_stub, &hardswish_kernel); -ALSO_REGISTER_AVX512_DISPATCH(hardswish_backward_stub, &hardswish_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(softplus_stub, &softplus_kernel); -ALSO_REGISTER_AVX512_DISPATCH(softplus_backward_stub, &softplus_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(silu_stub, &silu_kernel); -ALSO_REGISTER_AVX512_DISPATCH(silu_backward_stub, &silu_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(mish_stub, &mish_kernel); -ALSO_REGISTER_AVX512_DISPATCH(mish_backward_stub, &mish_backward_kernel); +ALSO_REGISTER_AVX512_DISPATCH(log_sigmoid_cpu_stub, &log_sigmoid_cpu_kernel) +ALSO_REGISTER_AVX512_DISPATCH(log_sigmoid_backward_stub, &log_sigmoid_backward_cpu_kernel) +ALSO_REGISTER_AVX512_DISPATCH(glu_stub, &glu_kernel) +ALSO_REGISTER_AVX512_DISPATCH(glu_backward_stub, &glu_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(glu_jvp_stub, &glu_jvp_kernel) +ALSO_REGISTER_AVX512_DISPATCH(elu_stub, &elu_kernel) +ALSO_REGISTER_AVX512_DISPATCH(elu_backward_stub, &elu_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(GeluKernel, &GeluKernelImpl) +ALSO_REGISTER_AVX512_DISPATCH(GeluBackwardKernel, &GeluBackwardKernelImpl) +ALSO_REGISTER_AVX512_DISPATCH(hardswish_stub, &hardswish_kernel) +ALSO_REGISTER_AVX512_DISPATCH(hardswish_backward_stub, &hardswish_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(softplus_stub, &softplus_kernel) +ALSO_REGISTER_AVX512_DISPATCH(softplus_backward_stub, &softplus_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(silu_stub, &silu_kernel) +ALSO_REGISTER_AVX512_DISPATCH(silu_backward_stub, &silu_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(mish_stub, &mish_kernel) +ALSO_REGISTER_AVX512_DISPATCH(mish_backward_stub, &mish_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp b/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp index 03e7817fff2..9891d6034ff 100644 --- a/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp +++ b/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp @@ -1430,17 +1430,17 @@ REGISTER_DISPATCH(chebyshev_polynomial_u_stub, &chebyshev_polynomial_u_kernel) REGISTER_DISPATCH(hermite_polynomial_h_stub, &hermite_polynomial_h_kernel) REGISTER_DISPATCH(hermite_polynomial_he_stub, &hermite_polynomial_he_kernel) -ALSO_REGISTER_AVX512_DISPATCH(atan2_stub, &atan2_kernel); -ALSO_REGISTER_AVX512_DISPATCH(smooth_l1_stub, &smooth_l1_kernel); -ALSO_REGISTER_AVX512_DISPATCH(huber_stub, &huber_kernel); -ALSO_REGISTER_AVX512_DISPATCH(sigmoid_backward_stub, &sigmoid_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(logit_backward_stub, &logit_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(tanh_backward_stub, &tanh_backward_kernel); -ALSO_REGISTER_AVX512_DISPATCH(mse_stub, &mse_kernel); -ALSO_REGISTER_AVX512_DISPATCH(logaddexp_stub, &logaddexp_kernel); -ALSO_REGISTER_AVX512_DISPATCH(logaddexp2_stub, &logaddexp2_kernel); -ALSO_REGISTER_AVX512_DISPATCH(hypot_stub, &hypot_kernel); -ALSO_REGISTER_AVX512_DISPATCH(igamma_stub, &igamma_kernel); -ALSO_REGISTER_AVX512_DISPATCH(igammac_stub, &igammac_kernel); +ALSO_REGISTER_AVX512_DISPATCH(atan2_stub, &atan2_kernel) +ALSO_REGISTER_AVX512_DISPATCH(smooth_l1_stub, &smooth_l1_kernel) +ALSO_REGISTER_AVX512_DISPATCH(huber_stub, &huber_kernel) +ALSO_REGISTER_AVX512_DISPATCH(sigmoid_backward_stub, &sigmoid_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(logit_backward_stub, &logit_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(tanh_backward_stub, &tanh_backward_kernel) +ALSO_REGISTER_AVX512_DISPATCH(mse_stub, &mse_kernel) +ALSO_REGISTER_AVX512_DISPATCH(logaddexp_stub, &logaddexp_kernel) +ALSO_REGISTER_AVX512_DISPATCH(logaddexp2_stub, &logaddexp2_kernel) +ALSO_REGISTER_AVX512_DISPATCH(hypot_stub, &hypot_kernel) +ALSO_REGISTER_AVX512_DISPATCH(igamma_stub, &igamma_kernel) +ALSO_REGISTER_AVX512_DISPATCH(igammac_stub, &igammac_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cpu/ComplexKernel.cpp b/aten/src/ATen/native/cpu/ComplexKernel.cpp index ccd4bbdb841..6cccbdd075a 100644 --- a/aten/src/ATen/native/cpu/ComplexKernel.cpp +++ b/aten/src/ATen/native/cpu/ComplexKernel.cpp @@ -26,6 +26,6 @@ void polar_kernel(TensorIterator& iter) { } // anonymous namespace REGISTER_DISPATCH(complex_stub, &complex_kernel) -ALSO_REGISTER_AVX512_DISPATCH(polar_stub, &polar_kernel); +ALSO_REGISTER_AVX512_DISPATCH(polar_stub, &polar_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cpu/DepthwiseConvKernel.cpp b/aten/src/ATen/native/cpu/DepthwiseConvKernel.cpp index df4b1eb9b16..6526a430822 100644 --- a/aten/src/ATen/native/cpu/DepthwiseConvKernel.cpp +++ b/aten/src/ATen/native/cpu/DepthwiseConvKernel.cpp @@ -520,6 +520,6 @@ Tensor _convolution_depthwise3x3_winograd( } // namespace -ALSO_REGISTER_AVX512_DISPATCH(convolution_depthwise3x3_winograd_stub, &_convolution_depthwise3x3_winograd); +ALSO_REGISTER_AVX512_DISPATCH(convolution_depthwise3x3_winograd_stub, &_convolution_depthwise3x3_winograd) } // namespace at::native diff --git a/aten/src/ATen/native/cpu/FlashAttentionKernel.cpp b/aten/src/ATen/native/cpu/FlashAttentionKernel.cpp index 981a470c445..e9c4c3f409c 100644 --- a/aten/src/ATen/native/cpu/FlashAttentionKernel.cpp +++ b/aten/src/ATen/native/cpu/FlashAttentionKernel.cpp @@ -1265,7 +1265,7 @@ void flash_attention_backward_kernel_impl( } // anonymous namespace -ALSO_REGISTER_AVX512_DISPATCH(flash_attention_kernel, &flash_attention_kernel_impl); -ALSO_REGISTER_AVX512_DISPATCH(flash_attention_backward_kernel, &flash_attention_backward_kernel_impl); +ALSO_REGISTER_AVX512_DISPATCH(flash_attention_kernel, &flash_attention_kernel_impl) +ALSO_REGISTER_AVX512_DISPATCH(flash_attention_backward_kernel, &flash_attention_backward_kernel_impl) } // at::native diff --git a/aten/src/ATen/native/cpu/PowKernel.cpp b/aten/src/ATen/native/cpu/PowKernel.cpp index 6885e096fb9..2cf751f0511 100644 --- a/aten/src/ATen/native/cpu/PowKernel.cpp +++ b/aten/src/ATen/native/cpu/PowKernel.cpp @@ -144,7 +144,7 @@ static void pow_tensor_scalar_kernel( } // anonymous namespace -ALSO_REGISTER_AVX512_DISPATCH(pow_tensor_tensor_stub, &CPU_CAPABILITY::pow_tensor_tensor_kernel); -ALSO_REGISTER_AVX512_DISPATCH(pow_tensor_scalar_stub, &CPU_CAPABILITY::pow_tensor_scalar_kernel); +ALSO_REGISTER_AVX512_DISPATCH(pow_tensor_tensor_stub, &CPU_CAPABILITY::pow_tensor_tensor_kernel) +ALSO_REGISTER_AVX512_DISPATCH(pow_tensor_scalar_stub, &CPU_CAPABILITY::pow_tensor_scalar_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cpu/SoftMaxKernel.cpp b/aten/src/ATen/native/cpu/SoftMaxKernel.cpp index aa1d1956518..c289152db04 100644 --- a/aten/src/ATen/native/cpu/SoftMaxKernel.cpp +++ b/aten/src/ATen/native/cpu/SoftMaxKernel.cpp @@ -1291,8 +1291,8 @@ static void log_softmax_backward_kernel_impl( } // anonymous namespace -ALSO_REGISTER_AVX512_DISPATCH(softmax_lastdim_kernel, &softmax_lastdim_kernel_impl); -ALSO_REGISTER_AVX512_DISPATCH(log_softmax_lastdim_kernel, &log_softmax_lastdim_kernel_impl); +ALSO_REGISTER_AVX512_DISPATCH(softmax_lastdim_kernel, &softmax_lastdim_kernel_impl) +ALSO_REGISTER_AVX512_DISPATCH(log_softmax_lastdim_kernel, &log_softmax_lastdim_kernel_impl) ALSO_REGISTER_AVX512_DISPATCH( softmax_backward_lastdim_kernel, &softmax_backward_lastdim_kernel_impl); @@ -1300,9 +1300,9 @@ ALSO_REGISTER_AVX512_DISPATCH( log_softmax_backward_lastdim_kernel, &log_softmax_backward_lastdim_kernel_impl); -ALSO_REGISTER_AVX512_DISPATCH(softmax_kernel, &softmax_kernel_impl); -ALSO_REGISTER_AVX512_DISPATCH(log_softmax_kernel, &log_softmax_kernel_impl); -ALSO_REGISTER_AVX512_DISPATCH(softmax_backward_kernel, &softmax_backward_kernel_impl); +ALSO_REGISTER_AVX512_DISPATCH(softmax_kernel, &softmax_kernel_impl) +ALSO_REGISTER_AVX512_DISPATCH(log_softmax_kernel, &log_softmax_kernel_impl) +ALSO_REGISTER_AVX512_DISPATCH(softmax_backward_kernel, &softmax_backward_kernel_impl) ALSO_REGISTER_AVX512_DISPATCH( log_softmax_backward_kernel, &log_softmax_backward_kernel_impl); diff --git a/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp b/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp index d348af2389f..fb647349e94 100644 --- a/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp +++ b/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp @@ -842,15 +842,15 @@ STATIC_IMPLEMENT_COMPLEX_KERNEL_WITHOUT_AVX512(tan); // The following kernels are compute-intensive & are compiled with both AVX512 // & AVX2 -ALSO_REGISTER_AVX512_DISPATCH(sign_stub, &CPU_CAPABILITY::sign_kernel); -ALSO_REGISTER_AVX512_DISPATCH(sgn_stub, &CPU_CAPABILITY::sgn_kernel); -ALSO_REGISTER_AVX512_DISPATCH(reciprocal_stub, &CPU_CAPABILITY::reciprocal_kernel); -ALSO_REGISTER_AVX512_DISPATCH(exp2_stub, &CPU_CAPABILITY::exp2_kernel); -ALSO_REGISTER_AVX512_DISPATCH(sigmoid_stub, &CPU_CAPABILITY::sigmoid_kernel); -ALSO_REGISTER_AVX512_DISPATCH(logit_stub, &CPU_CAPABILITY::logit_kernel); -ALSO_REGISTER_AVX512_DISPATCH(sinh_stub, &CPU_CAPABILITY::sinh_kernel); -ALSO_REGISTER_AVX512_DISPATCH(cosh_stub, &CPU_CAPABILITY::cosh_kernel); -ALSO_REGISTER_AVX512_DISPATCH(atanh_stub, &CPU_CAPABILITY::atanh_kernel); +ALSO_REGISTER_AVX512_DISPATCH(sign_stub, &CPU_CAPABILITY::sign_kernel) +ALSO_REGISTER_AVX512_DISPATCH(sgn_stub, &CPU_CAPABILITY::sgn_kernel) +ALSO_REGISTER_AVX512_DISPATCH(reciprocal_stub, &CPU_CAPABILITY::reciprocal_kernel) +ALSO_REGISTER_AVX512_DISPATCH(exp2_stub, &CPU_CAPABILITY::exp2_kernel) +ALSO_REGISTER_AVX512_DISPATCH(sigmoid_stub, &CPU_CAPABILITY::sigmoid_kernel) +ALSO_REGISTER_AVX512_DISPATCH(logit_stub, &CPU_CAPABILITY::logit_kernel) +ALSO_REGISTER_AVX512_DISPATCH(sinh_stub, &CPU_CAPABILITY::sinh_kernel) +ALSO_REGISTER_AVX512_DISPATCH(cosh_stub, &CPU_CAPABILITY::cosh_kernel) +ALSO_REGISTER_AVX512_DISPATCH(atanh_stub, &CPU_CAPABILITY::atanh_kernel) // Might enable AVX512 dispatch after enabling explicit vectorization for them REGISTER_DISPATCH(acosh_stub, &CPU_CAPABILITY::acosh_kernel) diff --git a/aten/src/ATen/native/cpu/int4mm_kernel.cpp b/aten/src/ATen/native/cpu/int4mm_kernel.cpp index 662f3af1425..ce433c597ce 100644 --- a/aten/src/ATen/native/cpu/int4mm_kernel.cpp +++ b/aten/src/ATen/native/cpu/int4mm_kernel.cpp @@ -775,8 +775,8 @@ void int4pack_mm_kernel( } // anonymous namespace -ALSO_REGISTER_AVX512_DISPATCH(weight_to_int4pack_stub, &weight_to_int4pack_kernel); -ALSO_REGISTER_AVX512_DISPATCH(int4pack_mm_stub, &int4pack_mm_kernel); +ALSO_REGISTER_AVX512_DISPATCH(weight_to_int4pack_stub, &weight_to_int4pack_kernel) +ALSO_REGISTER_AVX512_DISPATCH(int4pack_mm_stub, &int4pack_mm_kernel) } // at::native C10_DIAGNOSTIC_POP() diff --git a/aten/src/ATen/native/cpu/int8mm_kernel.cpp b/aten/src/ATen/native/cpu/int8mm_kernel.cpp index d61a1933afc..34a77a88b1e 100644 --- a/aten/src/ATen/native/cpu/int8mm_kernel.cpp +++ b/aten/src/ATen/native/cpu/int8mm_kernel.cpp @@ -433,6 +433,6 @@ void int8pack_mm_kernel( } // anonymous namespace -ALSO_REGISTER_AVX512_DISPATCH(int8pack_mm_stub, &int8pack_mm_kernel); +ALSO_REGISTER_AVX512_DISPATCH(int8pack_mm_stub, &int8pack_mm_kernel) } // at::native diff --git a/aten/src/ATen/native/cuda/AbsKernel.cu b/aten/src/ATen/native/cuda/AbsKernel.cu index e2c0a456a23..b20002d766a 100644 --- a/aten/src/ATen/native/cuda/AbsKernel.cu +++ b/aten/src/ATen/native/cuda/AbsKernel.cu @@ -46,6 +46,6 @@ void abs_kernel_cuda(TensorIteratorBase& iter) { } } - REGISTER_DISPATCH(abs_stub, &abs_kernel_cuda); + REGISTER_DISPATCH(abs_stub, &abs_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationEluKernel.cu b/aten/src/ATen/native/cuda/ActivationEluKernel.cu index 3f68b521c00..5ad1f806f9b 100644 --- a/aten/src/ATen/native/cuda/ActivationEluKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationEluKernel.cu @@ -80,7 +80,7 @@ void elu_backward_kernel( } } // namespace -REGISTER_DISPATCH(elu_stub, &elu_kernel); -REGISTER_DISPATCH(elu_backward_stub, &elu_backward_kernel); +REGISTER_DISPATCH(elu_stub, &elu_kernel) +REGISTER_DISPATCH(elu_backward_stub, &elu_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationGluKernel.cu b/aten/src/ATen/native/cuda/ActivationGluKernel.cu index 21fbc178bb4..e28a6d61ea1 100644 --- a/aten/src/ATen/native/cuda/ActivationGluKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationGluKernel.cu @@ -135,7 +135,7 @@ void launch_glu_backward_kernel( }); } -REGISTER_DISPATCH(glu_stub, &glu_kernel); -REGISTER_DISPATCH(glu_jvp_stub, &glu_jvp_kernel); +REGISTER_DISPATCH(glu_stub, &glu_kernel) +REGISTER_DISPATCH(glu_jvp_stub, &glu_jvp_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu b/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu index 3e2ca62e274..2a0be3f5d27 100644 --- a/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu @@ -34,6 +34,6 @@ void hardshrink_kernel(TensorIteratorBase& iter, const Scalar& value) { } } // namespace -REGISTER_DISPATCH(hardshrink_stub, &hardshrink_kernel); +REGISTER_DISPATCH(hardshrink_stub, &hardshrink_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu b/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu index f69b5c5daed..8a3326fddb8 100644 --- a/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu @@ -68,7 +68,7 @@ void hardsigmoid_backward_kernel(TensorIteratorBase& iter) { } // namespace -REGISTER_DISPATCH(hardsigmoid_stub, &hardsigmoid_kernel); -REGISTER_DISPATCH(hardsigmoid_backward_stub, &hardsigmoid_backward_kernel); +REGISTER_DISPATCH(hardsigmoid_stub, &hardsigmoid_kernel) +REGISTER_DISPATCH(hardsigmoid_backward_stub, &hardsigmoid_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu b/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu index 38011e9ed60..359c94c4733 100644 --- a/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu @@ -57,7 +57,7 @@ void hardswish_backward_kernel(TensorIterator& iter) { } } // namespace -REGISTER_DISPATCH(hardswish_stub, &hardswish_kernel); -REGISTER_DISPATCH(hardswish_backward_stub, &hardswish_backward_kernel); +REGISTER_DISPATCH(hardswish_stub, &hardswish_kernel) +REGISTER_DISPATCH(hardswish_backward_stub, &hardswish_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu b/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu index 30bb909d58e..a18072f7a27 100644 --- a/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu @@ -40,6 +40,6 @@ void hardtanh_backward_kernel( } } // namespace -REGISTER_DISPATCH(hardtanh_backward_stub, &hardtanh_backward_kernel); +REGISTER_DISPATCH(hardtanh_backward_stub, &hardtanh_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu b/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu index 6b848df333a..72130739898 100644 --- a/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu @@ -56,7 +56,7 @@ void leaky_relu_backward_kernel( } } // namespace -REGISTER_DISPATCH(leaky_relu_stub, &leaky_relu_kernel); -REGISTER_DISPATCH(leaky_relu_backward_stub, &leaky_relu_backward_kernel); +REGISTER_DISPATCH(leaky_relu_stub, &leaky_relu_kernel) +REGISTER_DISPATCH(leaky_relu_backward_stub, &leaky_relu_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu b/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu index eb34d9d4633..9a1d672428b 100644 --- a/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu @@ -59,6 +59,6 @@ void log_sigmoid_backward_kernel(TensorIterator& iter) { } } // namespace -REGISTER_DISPATCH(log_sigmoid_backward_stub, &log_sigmoid_backward_kernel); +REGISTER_DISPATCH(log_sigmoid_backward_stub, &log_sigmoid_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationMishKernel.cu b/aten/src/ATen/native/cuda/ActivationMishKernel.cu index e259e64fc08..0db0e96bb18 100644 --- a/aten/src/ATen/native/cuda/ActivationMishKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationMishKernel.cu @@ -58,7 +58,7 @@ void mish_backward_kernel(TensorIterator& iter) { } } // namespace -REGISTER_DISPATCH(mish_stub, &mish_kernel); -REGISTER_DISPATCH(mish_backward_stub, &mish_backward_kernel); +REGISTER_DISPATCH(mish_stub, &mish_kernel) +REGISTER_DISPATCH(mish_backward_stub, &mish_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationPreluKernel.cu b/aten/src/ATen/native/cuda/ActivationPreluKernel.cu index d6b73317738..b193690a20a 100644 --- a/aten/src/ATen/native/cuda/ActivationPreluKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationPreluKernel.cu @@ -42,7 +42,7 @@ void prelu_backward_kernel(TensorIterator &iter) { }); } -REGISTER_DISPATCH(prelu_stub, &prelu_kernel); -REGISTER_DISPATCH(prelu_backward_stub, &prelu_backward_kernel); +REGISTER_DISPATCH(prelu_stub, &prelu_kernel) +REGISTER_DISPATCH(prelu_backward_stub, &prelu_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationSiluKernel.cu b/aten/src/ATen/native/cuda/ActivationSiluKernel.cu index 82096b96dbb..f7ddfd8502a 100644 --- a/aten/src/ATen/native/cuda/ActivationSiluKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationSiluKernel.cu @@ -54,7 +54,7 @@ void silu_backward_kernel(TensorIteratorBase& iter) { } } // namespace -REGISTER_DISPATCH(silu_stub, &silu_kernel); -REGISTER_DISPATCH(silu_backward_stub, &silu_backward_kernel); +REGISTER_DISPATCH(silu_stub, &silu_kernel) +REGISTER_DISPATCH(silu_backward_stub, &silu_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationSoftplusKernel.cu b/aten/src/ATen/native/cuda/ActivationSoftplusKernel.cu index 054e42139b0..64ffc211237 100644 --- a/aten/src/ATen/native/cuda/ActivationSoftplusKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationSoftplusKernel.cu @@ -68,7 +68,7 @@ void softplus_backward_kernel( } // namespace -REGISTER_DISPATCH(softplus_stub, &softplus_kernel); -REGISTER_DISPATCH(softplus_backward_stub, &softplus_backward_kernel); +REGISTER_DISPATCH(softplus_stub, &softplus_kernel) +REGISTER_DISPATCH(softplus_backward_stub, &softplus_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationSoftshrinkKernel.cu b/aten/src/ATen/native/cuda/ActivationSoftshrinkKernel.cu index a07d0d69a38..d4f74f78c47 100644 --- a/aten/src/ATen/native/cuda/ActivationSoftshrinkKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationSoftshrinkKernel.cu @@ -52,7 +52,7 @@ void shrink_backward_kernel(TensorIteratorBase& iter, const Scalar& value) { } } // namespace -REGISTER_DISPATCH(softshrink_stub, &softshrink_kernel); -REGISTER_DISPATCH(shrink_backward_stub, &shrink_backward_kernel); +REGISTER_DISPATCH(softshrink_stub, &softshrink_kernel) +REGISTER_DISPATCH(shrink_backward_stub, &shrink_backward_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ActivationThresholdKernel.cu b/aten/src/ATen/native/cuda/ActivationThresholdKernel.cu index 68baa5133e7..2d1cb4a47d7 100644 --- a/aten/src/ATen/native/cuda/ActivationThresholdKernel.cu +++ b/aten/src/ATen/native/cuda/ActivationThresholdKernel.cu @@ -47,6 +47,6 @@ static void threshold_kernel_cuda( } // namespace -REGISTER_DISPATCH(threshold_stub, &threshold_kernel_cuda); +REGISTER_DISPATCH(threshold_stub, &threshold_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryBitwiseOpsKernels.cu b/aten/src/ATen/native/cuda/BinaryBitwiseOpsKernels.cu index f0a498b0647..c23fb614087 100644 --- a/aten/src/ATen/native/cuda/BinaryBitwiseOpsKernels.cu +++ b/aten/src/ATen/native/cuda/BinaryBitwiseOpsKernels.cu @@ -73,9 +73,9 @@ void bitwise_xor_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(bitwise_and_stub, &bitwise_and_kernel_cuda); -REGISTER_DISPATCH(bitwise_or_stub, &bitwise_or_kernel_cuda); -REGISTER_DISPATCH(bitwise_xor_stub, &bitwise_xor_kernel_cuda); +REGISTER_DISPATCH(bitwise_and_stub, &bitwise_and_kernel_cuda) +REGISTER_DISPATCH(bitwise_or_stub, &bitwise_or_kernel_cuda) +REGISTER_DISPATCH(bitwise_xor_stub, &bitwise_xor_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryDivFloorKernel.cu b/aten/src/ATen/native/cuda/BinaryDivFloorKernel.cu index 8bb754c36b8..bdfec7faffe 100644 --- a/aten/src/ATen/native/cuda/BinaryDivFloorKernel.cu +++ b/aten/src/ATen/native/cuda/BinaryDivFloorKernel.cu @@ -78,6 +78,6 @@ void div_floor_kernel_cuda(TensorIteratorBase& iter) { } } // namespace binary_internal -REGISTER_DISPATCH(div_floor_stub, &binary_internal::div_floor_kernel_cuda); +REGISTER_DISPATCH(div_floor_stub, &binary_internal::div_floor_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryDivTrueKernel.cu b/aten/src/ATen/native/cuda/BinaryDivTrueKernel.cu index a7fa53fcb0a..f3dfc2ba11a 100644 --- a/aten/src/ATen/native/cuda/BinaryDivTrueKernel.cu +++ b/aten/src/ATen/native/cuda/BinaryDivTrueKernel.cu @@ -56,6 +56,6 @@ void div_true_kernel_cuda(TensorIteratorBase& iter) { } } // namespace binary_internal -REGISTER_DISPATCH(div_true_stub, &binary_internal::div_true_kernel_cuda); +REGISTER_DISPATCH(div_true_stub, &binary_internal::div_true_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryDivTruncKernel.cu b/aten/src/ATen/native/cuda/BinaryDivTruncKernel.cu index 5e906a000b0..6690b557478 100644 --- a/aten/src/ATen/native/cuda/BinaryDivTruncKernel.cu +++ b/aten/src/ATen/native/cuda/BinaryDivTruncKernel.cu @@ -48,6 +48,6 @@ void div_trunc_kernel_cuda(TensorIteratorBase& iter) { } } // namespace binary_internal -REGISTER_DISPATCH(div_trunc_stub, &binary_internal::div_trunc_kernel_cuda); +REGISTER_DISPATCH(div_trunc_stub, &binary_internal::div_trunc_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryGeometricKernels.cu b/aten/src/ATen/native/cuda/BinaryGeometricKernels.cu index e734a66e931..485da72f7be 100644 --- a/aten/src/ATen/native/cuda/BinaryGeometricKernels.cu +++ b/aten/src/ATen/native/cuda/BinaryGeometricKernels.cu @@ -33,7 +33,7 @@ void hypot_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(atan2_stub, &atan2_kernel_cuda); -REGISTER_DISPATCH(hypot_stub, &hypot_kernel_cuda); +REGISTER_DISPATCH(atan2_stub, &atan2_kernel_cuda) +REGISTER_DISPATCH(hypot_stub, &hypot_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryLogicalOpsKernels.cu b/aten/src/ATen/native/cuda/BinaryLogicalOpsKernels.cu index 918a6ba4e98..3c8b99840c8 100644 --- a/aten/src/ATen/native/cuda/BinaryLogicalOpsKernels.cu +++ b/aten/src/ATen/native/cuda/BinaryLogicalOpsKernels.cu @@ -120,9 +120,9 @@ void logical_xor_kernel_cuda(TensorIterator& iter) { } } -REGISTER_DISPATCH(logical_and_stub, &logical_and_kernel_cuda); -REGISTER_DISPATCH(logical_or_stub, &logical_or_kernel_cuda); -REGISTER_DISPATCH(logical_xor_stub, &logical_xor_kernel_cuda); +REGISTER_DISPATCH(logical_and_stub, &logical_and_kernel_cuda) +REGISTER_DISPATCH(logical_or_stub, &logical_or_kernel_cuda) +REGISTER_DISPATCH(logical_xor_stub, &logical_xor_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryMiscBackwardOpsKernels.cu b/aten/src/ATen/native/cuda/BinaryMiscBackwardOpsKernels.cu index 0cd4c5040fe..cee150fb904 100644 --- a/aten/src/ATen/native/cuda/BinaryMiscBackwardOpsKernels.cu +++ b/aten/src/ATen/native/cuda/BinaryMiscBackwardOpsKernels.cu @@ -124,8 +124,8 @@ void tanh_backward_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(sigmoid_backward_stub, &sigmoid_backward_kernel_cuda); -REGISTER_DISPATCH(logit_backward_stub, &logit_backward_kernel_cuda); -REGISTER_DISPATCH(tanh_backward_stub, &tanh_backward_kernel_cuda); +REGISTER_DISPATCH(sigmoid_backward_stub, &sigmoid_backward_kernel_cuda) +REGISTER_DISPATCH(logit_backward_stub, &logit_backward_kernel_cuda) +REGISTER_DISPATCH(tanh_backward_stub, &tanh_backward_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryMiscOpsKernels.cu b/aten/src/ATen/native/cuda/BinaryMiscOpsKernels.cu index 5204e994a06..ace870698e7 100644 --- a/aten/src/ATen/native/cuda/BinaryMiscOpsKernels.cu +++ b/aten/src/ATen/native/cuda/BinaryMiscOpsKernels.cu @@ -69,11 +69,11 @@ void xlog1py_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(smooth_l1_stub, &smooth_l1_kernel_cuda); -REGISTER_DISPATCH(huber_stub, &huber_kernel_cuda); -REGISTER_DISPATCH(mse_stub, &mse_kernel_cuda); -REGISTER_DISPATCH(xlogy_stub, &xlogy_kernel_cuda); -REGISTER_DISPATCH(xlog1py_stub, &xlog1py_kernel_cuda); +REGISTER_DISPATCH(smooth_l1_stub, &smooth_l1_kernel_cuda) +REGISTER_DISPATCH(huber_stub, &huber_kernel_cuda) +REGISTER_DISPATCH(mse_stub, &mse_kernel_cuda) +REGISTER_DISPATCH(xlogy_stub, &xlogy_kernel_cuda) +REGISTER_DISPATCH(xlog1py_stub, &xlog1py_kernel_cuda) // DO NOT ADD ANY NEW KERNELS HERE // CUDA compilation times grow quickly. It's perfectly acceptable to have a file per kernel. diff --git a/aten/src/ATen/native/cuda/BinaryMulKernel.cu b/aten/src/ATen/native/cuda/BinaryMulKernel.cu index 242ff1c7cd5..26c4b15a7c6 100644 --- a/aten/src/ATen/native/cuda/BinaryMulKernel.cu +++ b/aten/src/ATen/native/cuda/BinaryMulKernel.cu @@ -43,6 +43,6 @@ void mul_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(mul_stub, &mul_kernel_cuda); +REGISTER_DISPATCH(mul_stub, &mul_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryRemainderKernel.cu b/aten/src/ATen/native/cuda/BinaryRemainderKernel.cu index dfa2f7124b5..d05db3dc582 100644 --- a/aten/src/ATen/native/cuda/BinaryRemainderKernel.cu +++ b/aten/src/ATen/native/cuda/BinaryRemainderKernel.cu @@ -55,7 +55,7 @@ void fmod_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(remainder_stub, &remainder_kernel_cuda); -REGISTER_DISPATCH(fmod_stub, &fmod_kernel_cuda); +REGISTER_DISPATCH(remainder_stub, &remainder_kernel_cuda) +REGISTER_DISPATCH(fmod_stub, &fmod_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/BinaryShiftOpsKernels.cu b/aten/src/ATen/native/cuda/BinaryShiftOpsKernels.cu index a7760d76ef5..287f4a2e10a 100644 --- a/aten/src/ATen/native/cuda/BinaryShiftOpsKernels.cu +++ b/aten/src/ATen/native/cuda/BinaryShiftOpsKernels.cu @@ -38,7 +38,7 @@ void rshift_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(lshift_stub, &lshift_kernel_cuda); -REGISTER_DISPATCH(rshift_stub, &rshift_kernel_cuda); +REGISTER_DISPATCH(lshift_stub, &lshift_kernel_cuda) +REGISTER_DISPATCH(rshift_stub, &rshift_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/CompareEQKernel.cu b/aten/src/ATen/native/cuda/CompareEQKernel.cu index 9496ae95d13..954d0b08a1d 100644 --- a/aten/src/ATen/native/cuda/CompareEQKernel.cu +++ b/aten/src/ATen/native/cuda/CompareEQKernel.cu @@ -44,7 +44,7 @@ void ne_kernel_cuda(TensorIteratorBase& iter) { compare_eq_ne_kernel(iter, EqOpType::NE); } -REGISTER_DISPATCH(eq_stub, &eq_kernel_cuda); -REGISTER_DISPATCH(ne_stub, &ne_kernel_cuda); +REGISTER_DISPATCH(eq_stub, &eq_kernel_cuda) +REGISTER_DISPATCH(ne_stub, &ne_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/CompareKernels.cu b/aten/src/ATen/native/cuda/CompareKernels.cu index 8a1a97759f1..047e1d3ef7b 100644 --- a/aten/src/ATen/native/cuda/CompareKernels.cu +++ b/aten/src/ATen/native/cuda/CompareKernels.cu @@ -95,9 +95,9 @@ void lt_kernel_cuda(TensorIteratorBase& iter) { compare_kernel_with_scalars(iter, OpType::LT); } -REGISTER_DISPATCH(ge_stub, &ge_kernel_cuda); -REGISTER_DISPATCH(gt_stub, >_kernel_cuda); -REGISTER_DISPATCH(le_stub, &le_kernel_cuda); -REGISTER_DISPATCH(lt_stub, <_kernel_cuda); +REGISTER_DISPATCH(ge_stub, &ge_kernel_cuda) +REGISTER_DISPATCH(gt_stub, >_kernel_cuda) +REGISTER_DISPATCH(le_stub, &le_kernel_cuda) +REGISTER_DISPATCH(lt_stub, <_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ComplexKernel.cu b/aten/src/ATen/native/cuda/ComplexKernel.cu index 2bf26722fbc..3328bb10a6e 100644 --- a/aten/src/ATen/native/cuda/ComplexKernel.cu +++ b/aten/src/ATen/native/cuda/ComplexKernel.cu @@ -30,7 +30,7 @@ void polar_kernel_cuda(TensorIterator& iter) { } // anonymous namespace -REGISTER_DISPATCH(complex_stub, &complex_kernel_cuda); -REGISTER_DISPATCH(polar_stub, &polar_kernel_cuda); +REGISTER_DISPATCH(complex_stub, &complex_kernel_cuda) +REGISTER_DISPATCH(polar_stub, &polar_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/Copy.cu b/aten/src/ATen/native/cuda/Copy.cu index 572a490242b..ff976795b29 100644 --- a/aten/src/ATen/native/cuda/Copy.cu +++ b/aten/src/ATen/native/cuda/Copy.cu @@ -410,6 +410,6 @@ static void copy_kernel_cuda(TensorIterator& iter, bool non_blocking) { } } -REGISTER_DISPATCH(copy_stub, ©_kernel_cuda); +REGISTER_DISPATCH(copy_stub, ©_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/CopysignKernel.cu b/aten/src/ATen/native/cuda/CopysignKernel.cu index 38724d7e299..ed385a23407 100644 --- a/aten/src/ATen/native/cuda/CopysignKernel.cu +++ b/aten/src/ATen/native/cuda/CopysignKernel.cu @@ -28,6 +28,6 @@ void copysign_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(copysign_stub, ©sign_kernel_cuda); +REGISTER_DISPATCH(copysign_stub, ©sign_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/CrossKernel.cu b/aten/src/ATen/native/cuda/CrossKernel.cu index 560d419c982..974b34ae67e 100644 --- a/aten/src/ATen/native/cuda/CrossKernel.cu +++ b/aten/src/ATen/native/cuda/CrossKernel.cu @@ -87,6 +87,6 @@ void cross_impl(const Tensor& result, const Tensor& x1, const Tensor& x2, int64_ } } -REGISTER_DISPATCH(cross_stub, &cross_impl); +REGISTER_DISPATCH(cross_stub, &cross_impl) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/DistanceKernel.cu b/aten/src/ATen/native/cuda/DistanceKernel.cu index 527e63f9325..d78aacac0d4 100644 --- a/aten/src/ATen/native/cuda/DistanceKernel.cu +++ b/aten/src/ATen/native/cuda/DistanceKernel.cu @@ -357,9 +357,9 @@ void cdist_backward_kernel_impl(Tensor& result, const Tensor& grad, const Tensor } // anonymous namespace -REGISTER_DISPATCH(pdist_forward_stub, &pdist_forward_kernel_impl); -REGISTER_DISPATCH(pdist_backward_stub, &pdist_backward_kernel_impl); -REGISTER_DISPATCH(cdist_stub, &cdist_kernel_impl); -REGISTER_DISPATCH(cdist_backward_stub, &cdist_backward_kernel_impl); +REGISTER_DISPATCH(pdist_forward_stub, &pdist_forward_kernel_impl) +REGISTER_DISPATCH(pdist_backward_stub, &pdist_backward_kernel_impl) +REGISTER_DISPATCH(cdist_stub, &cdist_kernel_impl) +REGISTER_DISPATCH(cdist_backward_stub, &cdist_backward_kernel_impl) } // at::native diff --git a/aten/src/ATen/native/cuda/DistributionBernoulli.cu b/aten/src/ATen/native/cuda/DistributionBernoulli.cu index 5a04ae9b345..8865aeaa3b9 100644 --- a/aten/src/ATen/native/cuda/DistributionBernoulli.cu +++ b/aten/src/ATen/native/cuda/DistributionBernoulli.cu @@ -34,7 +34,7 @@ void bernoulli_scalar_kernel(const TensorBase &self, double p, std::optional gen_) { at::native::templates::cuda::random_kernel(iter, gen); } -REGISTER_DISPATCH(random_from_to_stub, &random_from_to_kernel); -REGISTER_DISPATCH(random_stub, &random_kernel); -REGISTER_DISPATCH(random_full_64_bits_range_stub, &random_full_64_bits_range_kernel); +REGISTER_DISPATCH(random_from_to_stub, &random_from_to_kernel) +REGISTER_DISPATCH(random_stub, &random_kernel) +REGISTER_DISPATCH(random_full_64_bits_range_stub, &random_full_64_bits_range_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/DistributionUniform.cu b/aten/src/ATen/native/cuda/DistributionUniform.cu index ed34b78727d..c9c2383dbf8 100644 --- a/aten/src/ATen/native/cuda/DistributionUniform.cu +++ b/aten/src/ATen/native/cuda/DistributionUniform.cu @@ -10,6 +10,6 @@ void uniform_kernel(TensorIteratorBase& iter, double from, double to, std::optio templates::cuda::uniform_kernel(iter, from, to, generator); } -REGISTER_DISPATCH(uniform_stub, &uniform_kernel); +REGISTER_DISPATCH(uniform_stub, &uniform_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/FillKernel.cu b/aten/src/ATen/native/cuda/FillKernel.cu index dc2ecf2db35..266f0e49b8e 100644 --- a/aten/src/ATen/native/cuda/FillKernel.cu +++ b/aten/src/ATen/native/cuda/FillKernel.cu @@ -25,6 +25,6 @@ void fill_kernel_cuda(TensorIterator& iter, const Scalar& value) { }), AT_EXPAND(AT_ALL_TYPES_AND_COMPLEX), kComplexHalf, kBool, kHalf, kBFloat16, AT_EXPAND(AT_FLOAT8_TYPES), AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES)); } -REGISTER_DISPATCH(fill_stub, &fill_kernel_cuda); +REGISTER_DISPATCH(fill_stub, &fill_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/FunctionOfAMatrixUtilsKernel.cu b/aten/src/ATen/native/cuda/FunctionOfAMatrixUtilsKernel.cu index 683c9c058a3..4c5c700d30f 100644 --- a/aten/src/ATen/native/cuda/FunctionOfAMatrixUtilsKernel.cu +++ b/aten/src/ATen/native/cuda/FunctionOfAMatrixUtilsKernel.cu @@ -109,6 +109,6 @@ void _compute_linear_combination_cuda_kernel( } -REGISTER_DISPATCH(_compute_linear_combination_stub, &_compute_linear_combination_cuda_kernel); +REGISTER_DISPATCH(_compute_linear_combination_stub, &_compute_linear_combination_cuda_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/GcdLcmKernel.cu b/aten/src/ATen/native/cuda/GcdLcmKernel.cu index 6b003a6f4fc..2addfa12c2a 100644 --- a/aten/src/ATen/native/cuda/GcdLcmKernel.cu +++ b/aten/src/ATen/native/cuda/GcdLcmKernel.cu @@ -52,7 +52,7 @@ void lcm_kernel_cuda(TensorIteratorBase& iter) { #endif // AT_USE_JITERATOR() } -REGISTER_DISPATCH(gcd_stub, &gcd_kernel_cuda); -REGISTER_DISPATCH(lcm_stub, &lcm_kernel_cuda); +REGISTER_DISPATCH(gcd_stub, &gcd_kernel_cuda) +REGISTER_DISPATCH(lcm_stub, &lcm_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/IGammaKernel.cu b/aten/src/ATen/native/cuda/IGammaKernel.cu index 1c0f2fd2864..624f080d9f6 100644 --- a/aten/src/ATen/native/cuda/IGammaKernel.cu +++ b/aten/src/ATen/native/cuda/IGammaKernel.cu @@ -545,8 +545,8 @@ void igammac_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(igamma_stub, &igamma_kernel_cuda); -REGISTER_DISPATCH(igammac_stub, &igammac_kernel_cuda); +REGISTER_DISPATCH(igamma_stub, &igamma_kernel_cuda) +REGISTER_DISPATCH(igammac_stub, &igammac_kernel_cuda) // DO NOT ADD ANY NEW KERNELS HERE // CUDA compilation times grow quickly. It's perfectly acceptable to have a file per kernel. diff --git a/aten/src/ATen/native/cuda/IndexKernel.cu b/aten/src/ATen/native/cuda/IndexKernel.cu index 4f1a37ccf5e..bc2b406b43a 100644 --- a/aten/src/ATen/native/cuda/IndexKernel.cu +++ b/aten/src/ATen/native/cuda/IndexKernel.cu @@ -475,13 +475,13 @@ void flip_kernel(TensorIterator& iter, const bool quantized) { } -REGISTER_DISPATCH(index_stub, &index_kernel); -REGISTER_DISPATCH(index_fill_stub, &index_fill_kernel); -REGISTER_DISPATCH(index_copy_stub, &index_copy_kernel); -REGISTER_DISPATCH(index_put_stub, &index_put_kernel); -REGISTER_DISPATCH(put_stub, &put_kernel); -REGISTER_DISPATCH(take_stub, &take_kernel); -REGISTER_DISPATCH(flip_stub, &flip_kernel); +REGISTER_DISPATCH(index_stub, &index_kernel) +REGISTER_DISPATCH(index_fill_stub, &index_fill_kernel) +REGISTER_DISPATCH(index_copy_stub, &index_copy_kernel) +REGISTER_DISPATCH(index_put_stub, &index_put_kernel) +REGISTER_DISPATCH(put_stub, &put_kernel) +REGISTER_DISPATCH(take_stub, &take_kernel) +REGISTER_DISPATCH(flip_stub, &flip_kernel) REGISTER_CUDA_DISPATCH(index_put_kernel_quantized_stub, &index_put_kernel_quantized_cuda); diff --git a/aten/src/ATen/native/cuda/Lerp.cu b/aten/src/ATen/native/cuda/Lerp.cu index 25692dcd4c4..94fd7a40746 100644 --- a/aten/src/ATen/native/cuda/Lerp.cu +++ b/aten/src/ATen/native/cuda/Lerp.cu @@ -121,7 +121,7 @@ void lerp_scalar_kernel(at::TensorIteratorBase& iter, const c10::Scalar& weight) } // anonymous namespace -REGISTER_DISPATCH(lerp_kernel_tensor_weight, &lerp_tensor_kernel); -REGISTER_DISPATCH(lerp_kernel_scalar_weight, &lerp_scalar_kernel); +REGISTER_DISPATCH(lerp_kernel_tensor_weight, &lerp_tensor_kernel) +REGISTER_DISPATCH(lerp_kernel_scalar_weight, &lerp_scalar_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/LinearAlgebra.cu b/aten/src/ATen/native/cuda/LinearAlgebra.cu index a6a566a5de2..723cdbe9e55 100644 --- a/aten/src/ATen/native/cuda/LinearAlgebra.cu +++ b/aten/src/ATen/native/cuda/LinearAlgebra.cu @@ -139,6 +139,6 @@ void unpack_pivots_cuda_kernel(TensorIterator& iter, const int64_t dim_size, con } } // anonymous namespace -REGISTER_DISPATCH(unpack_pivots_stub, &unpack_pivots_cuda_kernel); -REGISTER_DISPATCH(addr_stub, &addr_kernel_cuda); +REGISTER_DISPATCH(unpack_pivots_stub, &unpack_pivots_cuda_kernel) +REGISTER_DISPATCH(addr_stub, &addr_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/LogAddExpKernel.cu b/aten/src/ATen/native/cuda/LogAddExpKernel.cu index 65cc46a1704..7b8b5b5bb20 100644 --- a/aten/src/ATen/native/cuda/LogAddExpKernel.cu +++ b/aten/src/ATen/native/cuda/LogAddExpKernel.cu @@ -51,7 +51,7 @@ void logaddexp2_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(logaddexp_stub, &logaddexp_kernel_cuda); -REGISTER_DISPATCH(logaddexp2_stub, &logaddexp2_kernel_cuda); +REGISTER_DISPATCH(logaddexp_stub, &logaddexp_kernel_cuda) +REGISTER_DISPATCH(logaddexp2_stub, &logaddexp2_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/MaxMinElementwiseKernel.cu b/aten/src/ATen/native/cuda/MaxMinElementwiseKernel.cu index 51c82e95213..f3bcdcc9148 100644 --- a/aten/src/ATen/native/cuda/MaxMinElementwiseKernel.cu +++ b/aten/src/ATen/native/cuda/MaxMinElementwiseKernel.cu @@ -90,9 +90,9 @@ void fmin_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(maximum_stub, &maximum_kernel_cuda); -REGISTER_DISPATCH(minimum_stub, &minimum_kernel_cuda); -REGISTER_DISPATCH(fmax_stub, &fmax_kernel_cuda); -REGISTER_DISPATCH(fmin_stub, &fmin_kernel_cuda); +REGISTER_DISPATCH(maximum_stub, &maximum_kernel_cuda) +REGISTER_DISPATCH(minimum_stub, &minimum_kernel_cuda) +REGISTER_DISPATCH(fmax_stub, &fmax_kernel_cuda) +REGISTER_DISPATCH(fmin_stub, &fmin_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/PointwiseOpsKernel.cu b/aten/src/ATen/native/cuda/PointwiseOpsKernel.cu index eee0047fd72..45b0d01ceeb 100644 --- a/aten/src/ATen/native/cuda/PointwiseOpsKernel.cu +++ b/aten/src/ATen/native/cuda/PointwiseOpsKernel.cu @@ -147,9 +147,9 @@ void mse_backward_cuda_kernel(TensorIterator& iter, const Scalar& value) { }); } -REGISTER_DISPATCH(addcdiv_stub, &addcdiv_cuda_kernel); -REGISTER_DISPATCH(addcmul_stub, &addcmul_cuda_kernel); -REGISTER_DISPATCH(smooth_l1_backward_stub, &smooth_l1_backward_cuda_kernel); -REGISTER_DISPATCH(huber_backward_stub, &huber_backward_cuda_kernel); -REGISTER_DISPATCH(mse_backward_stub, &mse_backward_cuda_kernel); +REGISTER_DISPATCH(addcdiv_stub, &addcdiv_cuda_kernel) +REGISTER_DISPATCH(addcmul_stub, &addcmul_cuda_kernel) +REGISTER_DISPATCH(smooth_l1_backward_stub, &smooth_l1_backward_cuda_kernel) +REGISTER_DISPATCH(huber_backward_stub, &huber_backward_cuda_kernel) +REGISTER_DISPATCH(mse_backward_stub, &mse_backward_cuda_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/PowKernel.cu b/aten/src/ATen/native/cuda/PowKernel.cu index 010818ca213..438f8336160 100644 --- a/aten/src/ATen/native/cuda/PowKernel.cu +++ b/aten/src/ATen/native/cuda/PowKernel.cu @@ -203,7 +203,7 @@ void pow_tensor_scalar_kernel(TensorIteratorBase& iter, const Scalar& exp_scalar } // anonymous namespace -REGISTER_DISPATCH(pow_tensor_tensor_stub, &pow_tensor_tensor_kernel); -REGISTER_DISPATCH(pow_tensor_scalar_stub, &pow_tensor_scalar_kernel); +REGISTER_DISPATCH(pow_tensor_tensor_stub, &pow_tensor_tensor_kernel) +REGISTER_DISPATCH(pow_tensor_scalar_stub, &pow_tensor_scalar_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ReduceArgMaxKernel.cu b/aten/src/ATen/native/cuda/ReduceArgMaxKernel.cu index c5d763f3135..d88ed2ac0f5 100644 --- a/aten/src/ATen/native/cuda/ReduceArgMaxKernel.cu +++ b/aten/src/ATen/native/cuda/ReduceArgMaxKernel.cu @@ -41,6 +41,6 @@ void argmax_kernel_cuda(TensorIterator& iter) { } } -REGISTER_DISPATCH(argmax_stub, &argmax_kernel_cuda); +REGISTER_DISPATCH(argmax_stub, &argmax_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ReduceArgMinKernel.cu b/aten/src/ATen/native/cuda/ReduceArgMinKernel.cu index fc34c11c519..44c44f6bf03 100644 --- a/aten/src/ATen/native/cuda/ReduceArgMinKernel.cu +++ b/aten/src/ATen/native/cuda/ReduceArgMinKernel.cu @@ -41,6 +41,6 @@ void argmin_kernel_cuda(TensorIterator& iter) { } } -REGISTER_DISPATCH(argmin_stub, &argmin_kernel_cuda); +REGISTER_DISPATCH(argmin_stub, &argmin_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ReduceLogicKernel.cu b/aten/src/ATen/native/cuda/ReduceLogicKernel.cu index 3f65c745d7a..9e806b2aa71 100644 --- a/aten/src/ATen/native/cuda/ReduceLogicKernel.cu +++ b/aten/src/ATen/native/cuda/ReduceLogicKernel.cu @@ -32,7 +32,7 @@ void or_kernel_cuda(TensorIterator& iter) { }); } -REGISTER_DISPATCH(and_stub, &and_kernel_cuda); -REGISTER_DISPATCH(or_stub, &or_kernel_cuda); +REGISTER_DISPATCH(and_stub, &and_kernel_cuda) +REGISTER_DISPATCH(or_stub, &or_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ReduceMaxValuesKernel.cu b/aten/src/ATen/native/cuda/ReduceMaxValuesKernel.cu index 883e8fe2149..e8d1e88ebb3 100644 --- a/aten/src/ATen/native/cuda/ReduceMaxValuesKernel.cu +++ b/aten/src/ATen/native/cuda/ReduceMaxValuesKernel.cu @@ -56,6 +56,6 @@ void max_all_launch_kernel(TensorIterator &iter) { }); } -REGISTER_DISPATCH(max_values_stub, &max_values_kernel_cuda); +REGISTER_DISPATCH(max_values_stub, &max_values_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ReduceMinValuesKernel.cu b/aten/src/ATen/native/cuda/ReduceMinValuesKernel.cu index a0ccf873be0..e01ca6c88eb 100644 --- a/aten/src/ATen/native/cuda/ReduceMinValuesKernel.cu +++ b/aten/src/ATen/native/cuda/ReduceMinValuesKernel.cu @@ -53,6 +53,6 @@ void min_all_launch_kernel(TensorIterator &iter) { }); } -REGISTER_DISPATCH(min_values_stub, &min_values_kernel_cuda); +REGISTER_DISPATCH(min_values_stub, &min_values_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ReduceMomentKernel.cu b/aten/src/ATen/native/cuda/ReduceMomentKernel.cu index 1b23132264a..d7d7fabecc9 100644 --- a/aten/src/ATen/native/cuda/ReduceMomentKernel.cu +++ b/aten/src/ATen/native/cuda/ReduceMomentKernel.cu @@ -62,7 +62,7 @@ static void mean_kernel_cuda(TensorIterator& iter) { } } -REGISTER_DISPATCH(std_var_stub, &std_var_kernel_cuda); -REGISTER_DISPATCH(mean_stub, &mean_kernel_cuda); +REGISTER_DISPATCH(std_var_stub, &std_var_kernel_cuda) +REGISTER_DISPATCH(mean_stub, &mean_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu b/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu index dc2f0fa492a..79eb3a31154 100644 --- a/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu +++ b/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu @@ -208,8 +208,8 @@ static void prod_kernel_cuda(TensorIterator& iter) { reduce_dispatch(iter, general_dispatcher); } -REGISTER_DISPATCH(sum_stub, &sum_kernel_cuda); -REGISTER_DISPATCH(nansum_stub, &nansum_kernel_cuda); -REGISTER_DISPATCH(prod_stub, &prod_kernel_cuda); +REGISTER_DISPATCH(sum_stub, &sum_kernel_cuda) +REGISTER_DISPATCH(nansum_stub, &nansum_kernel_cuda) +REGISTER_DISPATCH(prod_stub, &prod_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/RenormKernel.cu b/aten/src/ATen/native/cuda/RenormKernel.cu index ef133761aed..e625609deff 100644 --- a/aten/src/ATen/native/cuda/RenormKernel.cu +++ b/aten/src/ATen/native/cuda/RenormKernel.cu @@ -24,6 +24,6 @@ void renorm_scale_factor_impl(TensorIteratorBase& iter, double maxnorm) { } // namespace (anonymous) -REGISTER_DISPATCH(renorm_scale_factor_stub, &renorm_scale_factor_impl); +REGISTER_DISPATCH(renorm_scale_factor_stub, &renorm_scale_factor_impl) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ScatterGatherKernel.cu b/aten/src/ATen/native/cuda/ScatterGatherKernel.cu index 9ef83599cd1..e7642bf0893 100644 --- a/aten/src/ATen/native/cuda/ScatterGatherKernel.cu +++ b/aten/src/ATen/native/cuda/ScatterGatherKernel.cu @@ -562,12 +562,12 @@ void scatter_scalar_reduce_cuda_kernel(const Tensor& self, const int64_t dim, co } -REGISTER_DISPATCH(gather_stub, &gather_cuda_kernel); -REGISTER_DISPATCH(scatter_stub, &scatter_cuda_kernel); -REGISTER_DISPATCH(scatter_fill_stub, &scatter_fill_cuda_kernel); -REGISTER_DISPATCH(scatter_add_stub, &scatter_add_cuda_kernel); -REGISTER_DISPATCH(scatter_reduce_stub, &scatter_reduce_cuda_kernel); -REGISTER_DISPATCH(scatter_scalar_reduce_stub, &scatter_scalar_reduce_cuda_kernel); -REGISTER_DISPATCH(scatter_reduce_two_stub, &scatter_reduce_two_cuda_kernel); +REGISTER_DISPATCH(gather_stub, &gather_cuda_kernel) +REGISTER_DISPATCH(scatter_stub, &scatter_cuda_kernel) +REGISTER_DISPATCH(scatter_fill_stub, &scatter_fill_cuda_kernel) +REGISTER_DISPATCH(scatter_add_stub, &scatter_add_cuda_kernel) +REGISTER_DISPATCH(scatter_reduce_stub, &scatter_reduce_cuda_kernel) +REGISTER_DISPATCH(scatter_scalar_reduce_stub, &scatter_scalar_reduce_cuda_kernel) +REGISTER_DISPATCH(scatter_reduce_two_stub, &scatter_reduce_two_cuda_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/SegmentReduce.cu b/aten/src/ATen/native/cuda/SegmentReduce.cu index cbdbb020d63..0d8dbe67425 100644 --- a/aten/src/ATen/native/cuda/SegmentReduce.cu +++ b/aten/src/ATen/native/cuda/SegmentReduce.cu @@ -590,8 +590,8 @@ Tensor _segment_reduce_offsets_cuda_kernel( reduction, data, offsets, axis, initial, /*is_offsets_like=*/true); } -REGISTER_DISPATCH(_segment_reduce_lengths_stub, &_segment_reduce_lengths_cuda_kernel); -REGISTER_DISPATCH(_segment_reduce_offsets_stub, &_segment_reduce_offsets_cuda_kernel); +REGISTER_DISPATCH(_segment_reduce_lengths_stub, &_segment_reduce_lengths_cuda_kernel) +REGISTER_DISPATCH(_segment_reduce_offsets_stub, &_segment_reduce_offsets_cuda_kernel) REGISTER_DISPATCH( _segment_reduce_lengths_backward_stub, &_segment_reduce_lengths_backward_cuda_kernel); diff --git a/aten/src/ATen/native/cuda/SpectralOps.cu b/aten/src/ATen/native/cuda/SpectralOps.cu index 0141a6b952e..14e15665371 100644 --- a/aten/src/ATen/native/cuda/SpectralOps.cu +++ b/aten/src/ATen/native/cuda/SpectralOps.cu @@ -119,6 +119,6 @@ void _fft_fill_with_conjugate_symmetry_cuda_( }); } -REGISTER_DISPATCH(fft_fill_with_conjugate_symmetry_stub, &_fft_fill_with_conjugate_symmetry_cuda_); +REGISTER_DISPATCH(fft_fill_with_conjugate_symmetry_stub, &_fft_fill_with_conjugate_symmetry_cuda_) } // at::native diff --git a/aten/src/ATen/native/cuda/StepKernel.cu b/aten/src/ATen/native/cuda/StepKernel.cu index be2c3910ebe..5888e812862 100644 --- a/aten/src/ATen/native/cuda/StepKernel.cu +++ b/aten/src/ATen/native/cuda/StepKernel.cu @@ -27,7 +27,7 @@ void heaviside_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(nextafter_stub, &nextafter_kernel_cuda); -REGISTER_DISPATCH(heaviside_stub, &heaviside_kernel_cuda); +REGISTER_DISPATCH(nextafter_stub, &nextafter_kernel_cuda) +REGISTER_DISPATCH(heaviside_stub, &heaviside_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/TensorCompare.cu b/aten/src/ATen/native/cuda/TensorCompare.cu index 1a3ee09ac93..845e4767371 100644 --- a/aten/src/ATen/native/cuda/TensorCompare.cu +++ b/aten/src/ATen/native/cuda/TensorCompare.cu @@ -93,13 +93,13 @@ void clamp_max_scalar_kernel_impl(TensorIteratorBase& iter, Scalar max) { } // anonymous namespace -REGISTER_DISPATCH(where_kernel, &where_kernel_impl); -REGISTER_DISPATCH(isposinf_stub, &isposinf_kernel_impl); -REGISTER_DISPATCH(isneginf_stub, &isneginf_kernel_impl); -REGISTER_DISPATCH(clamp_stub, &clamp_kernel_impl); -REGISTER_DISPATCH(clamp_scalar_stub, &clamp_scalar_kernel_impl); -REGISTER_DISPATCH(clamp_min_scalar_stub, &clamp_min_scalar_kernel_impl); -REGISTER_DISPATCH(clamp_max_scalar_stub, &clamp_max_scalar_kernel_impl); +REGISTER_DISPATCH(where_kernel, &where_kernel_impl) +REGISTER_DISPATCH(isposinf_stub, &isposinf_kernel_impl) +REGISTER_DISPATCH(isneginf_stub, &isneginf_kernel_impl) +REGISTER_DISPATCH(clamp_stub, &clamp_kernel_impl) +REGISTER_DISPATCH(clamp_scalar_stub, &clamp_scalar_kernel_impl) +REGISTER_DISPATCH(clamp_min_scalar_stub, &clamp_min_scalar_kernel_impl) +REGISTER_DISPATCH(clamp_max_scalar_stub, &clamp_max_scalar_kernel_impl) struct Msg { static constexpr size_t MAX_MSG_LENGTH = 256; diff --git a/aten/src/ATen/native/cuda/UnaryComplexKernels.cu b/aten/src/ATen/native/cuda/UnaryComplexKernels.cu index 960414f63cd..97067dc2bc9 100644 --- a/aten/src/ATen/native/cuda/UnaryComplexKernels.cu +++ b/aten/src/ATen/native/cuda/UnaryComplexKernels.cu @@ -96,7 +96,7 @@ void conj_kernel_cuda(TensorIteratorBase& iter) { ); } -REGISTER_DISPATCH(angle_stub, &angle_kernel_cuda); -REGISTER_DISPATCH(conj_physical_stub, &conj_kernel_cuda); +REGISTER_DISPATCH(angle_stub, &angle_kernel_cuda) +REGISTER_DISPATCH(conj_physical_stub, &conj_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryFractionKernels.cu b/aten/src/ATen/native/cuda/UnaryFractionKernels.cu index e3529e55036..8a580e55d92 100644 --- a/aten/src/ATen/native/cuda/UnaryFractionKernels.cu +++ b/aten/src/ATen/native/cuda/UnaryFractionKernels.cu @@ -188,12 +188,12 @@ void trunc_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(ceil_stub, &ceil_kernel_cuda); -REGISTER_DISPATCH(frac_stub, &frac_kernel_cuda); -REGISTER_DISPATCH(floor_stub, &floor_kernel_cuda); -REGISTER_DISPATCH(reciprocal_stub, &reciprocal_kernel_cuda); -REGISTER_DISPATCH(round_stub, &round_kernel_cuda); -REGISTER_DISPATCH(round_decimals_stub, &round_decimals_kernel_cuda); -REGISTER_DISPATCH(trunc_stub, &trunc_kernel_cuda); +REGISTER_DISPATCH(ceil_stub, &ceil_kernel_cuda) +REGISTER_DISPATCH(frac_stub, &frac_kernel_cuda) +REGISTER_DISPATCH(floor_stub, &floor_kernel_cuda) +REGISTER_DISPATCH(reciprocal_stub, &reciprocal_kernel_cuda) +REGISTER_DISPATCH(round_stub, &round_kernel_cuda) +REGISTER_DISPATCH(round_decimals_stub, &round_decimals_kernel_cuda) +REGISTER_DISPATCH(trunc_stub, &trunc_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGammaKernels.cu b/aten/src/ATen/native/cuda/UnaryGammaKernels.cu index 6448335002c..28aa1a48b08 100644 --- a/aten/src/ATen/native/cuda/UnaryGammaKernels.cu +++ b/aten/src/ATen/native/cuda/UnaryGammaKernels.cu @@ -125,8 +125,8 @@ void lgamma_kernel_cuda(TensorIteratorBase& iter) { #endif } -REGISTER_DISPATCH(digamma_stub, &digamma_kernel_cuda); -REGISTER_DISPATCH(polygamma_stub, &polygamma_kernel_cuda); -REGISTER_DISPATCH(lgamma_stub, &lgamma_kernel_cuda); +REGISTER_DISPATCH(digamma_stub, &digamma_kernel_cuda) +REGISTER_DISPATCH(polygamma_stub, &polygamma_kernel_cuda) +REGISTER_DISPATCH(lgamma_stub, &lgamma_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricAcosKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricAcosKernel.cu index bd779fed2ab..a8a17a3c9ce 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricAcosKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricAcosKernel.cu @@ -53,6 +53,6 @@ void acos_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(acos_stub, &acos_kernel_cuda); +REGISTER_DISPATCH(acos_stub, &acos_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricAcoshKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricAcoshKernel.cu index ab178f6df1f..be75f83114a 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricAcoshKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricAcoshKernel.cu @@ -54,6 +54,6 @@ void acosh_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(acosh_stub, &acosh_kernel_cuda); +REGISTER_DISPATCH(acosh_stub, &acosh_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricAsinKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricAsinKernel.cu index 97a4e2b46e8..078622b81bd 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricAsinKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricAsinKernel.cu @@ -50,6 +50,6 @@ void asin_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(asin_stub, &asin_kernel_cuda); +REGISTER_DISPATCH(asin_stub, &asin_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricAsinhKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricAsinhKernel.cu index 1a0b2ce9e38..fd6fc04e884 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricAsinhKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricAsinhKernel.cu @@ -54,6 +54,6 @@ void asinh_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(asinh_stub, &asinh_kernel_cuda); +REGISTER_DISPATCH(asinh_stub, &asinh_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricAtanKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricAtanKernel.cu index 5018ac8a312..c34b44c6651 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricAtanKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricAtanKernel.cu @@ -53,6 +53,6 @@ void atan_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(atan_stub, &atan_kernel_cuda); +REGISTER_DISPATCH(atan_stub, &atan_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricAtanhKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricAtanhKernel.cu index 71b65815bfe..4489b5e7f4f 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricAtanhKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricAtanhKernel.cu @@ -53,6 +53,6 @@ void atanh_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(atanh_stub, &atanh_kernel_cuda); +REGISTER_DISPATCH(atanh_stub, &atanh_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricCosKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricCosKernel.cu index 0cac6ff79c3..5df095aae91 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricCosKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricCosKernel.cu @@ -52,6 +52,6 @@ void cos_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(cos_stub, &cos_kernel_cuda); +REGISTER_DISPATCH(cos_stub, &cos_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricCoshKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricCoshKernel.cu index a5e390c8ec3..210705a4e73 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricCoshKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricCoshKernel.cu @@ -53,6 +53,6 @@ void cosh_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(cosh_stub, &cosh_kernel_cuda); +REGISTER_DISPATCH(cosh_stub, &cosh_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricSinKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricSinKernel.cu index 3613192562e..351c5a714aa 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricSinKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricSinKernel.cu @@ -52,6 +52,6 @@ void sin_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(sin_stub, &sin_kernel_cuda); +REGISTER_DISPATCH(sin_stub, &sin_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricSinhKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricSinhKernel.cu index 039700c21be..b4dabd3a507 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricSinhKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricSinhKernel.cu @@ -53,6 +53,6 @@ void sinh_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(sinh_stub, &sinh_kernel_cuda); +REGISTER_DISPATCH(sinh_stub, &sinh_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricTanKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricTanKernel.cu index a71588e551c..34e055d589a 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricTanKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricTanKernel.cu @@ -52,6 +52,6 @@ void tan_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(tan_stub, &tan_kernel_cuda); +REGISTER_DISPATCH(tan_stub, &tan_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryGeometricTanhKernel.cu b/aten/src/ATen/native/cuda/UnaryGeometricTanhKernel.cu index 6a9f6a4cbdd..61393eec8ca 100644 --- a/aten/src/ATen/native/cuda/UnaryGeometricTanhKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryGeometricTanhKernel.cu @@ -53,6 +53,6 @@ void tanh_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(tanh_stub, &tanh_kernel_cuda); +REGISTER_DISPATCH(tanh_stub, &tanh_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryLogKernels.cu b/aten/src/ATen/native/cuda/UnaryLogKernels.cu index f213886319d..4c636a3d36f 100644 --- a/aten/src/ATen/native/cuda/UnaryLogKernels.cu +++ b/aten/src/ATen/native/cuda/UnaryLogKernels.cu @@ -113,9 +113,9 @@ void log2_kernel_cuda(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(log_stub, &log_kernel_cuda); -REGISTER_DISPATCH(log10_stub, &log10_kernel_cuda); -REGISTER_DISPATCH(log2_stub, &log2_kernel_cuda); -REGISTER_DISPATCH(log1p_stub, &log1p_kernel_cuda); +REGISTER_DISPATCH(log_stub, &log_kernel_cuda) +REGISTER_DISPATCH(log10_stub, &log10_kernel_cuda) +REGISTER_DISPATCH(log2_stub, &log2_kernel_cuda) +REGISTER_DISPATCH(log1p_stub, &log1p_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnaryOpsKernel.cu b/aten/src/ATen/native/cuda/UnaryOpsKernel.cu index 5eb64ab5725..6a0e21dc93f 100644 --- a/aten/src/ATen/native/cuda/UnaryOpsKernel.cu +++ b/aten/src/ATen/native/cuda/UnaryOpsKernel.cu @@ -275,12 +275,12 @@ void frexp_kernel_cuda(TensorIteratorBase& iter) { }); } -REGISTER_DISPATCH(bitwise_not_stub, &bitwise_not_kernel_cuda); -REGISTER_DISPATCH(exp_stub, &exp_kernel_cuda); -REGISTER_DISPATCH(expm1_stub, &expm1_kernel_cuda); -REGISTER_DISPATCH(rsqrt_stub, &rsqrt_kernel_cuda); -REGISTER_DISPATCH(sqrt_stub, &sqrt_kernel_cuda); -REGISTER_DISPATCH(nan_to_num_stub, &nan_to_num_kernel_cuda); -REGISTER_DISPATCH(frexp_stub, &frexp_kernel_cuda); +REGISTER_DISPATCH(bitwise_not_stub, &bitwise_not_kernel_cuda) +REGISTER_DISPATCH(exp_stub, &exp_kernel_cuda) +REGISTER_DISPATCH(expm1_stub, &expm1_kernel_cuda) +REGISTER_DISPATCH(rsqrt_stub, &rsqrt_kernel_cuda) +REGISTER_DISPATCH(sqrt_stub, &sqrt_kernel_cuda) +REGISTER_DISPATCH(nan_to_num_stub, &nan_to_num_kernel_cuda) +REGISTER_DISPATCH(frexp_stub, &frexp_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnarySignKernels.cu b/aten/src/ATen/native/cuda/UnarySignKernels.cu index 2a811e314c2..2736aa33bc2 100644 --- a/aten/src/ATen/native/cuda/UnarySignKernels.cu +++ b/aten/src/ATen/native/cuda/UnarySignKernels.cu @@ -128,10 +128,10 @@ void sgn_kernel_cuda(TensorIteratorBase& iter){ #endif } -REGISTER_DISPATCH(logical_not_stub, &logical_not_kernel_cuda); -REGISTER_DISPATCH(neg_stub, &neg_kernel_cuda); -REGISTER_DISPATCH(sign_stub, &sign_kernel_cuda); -REGISTER_DISPATCH(signbit_stub, &signbit_kernel_cuda); -REGISTER_DISPATCH(sgn_stub, &sgn_kernel_cuda); +REGISTER_DISPATCH(logical_not_stub, &logical_not_kernel_cuda) +REGISTER_DISPATCH(neg_stub, &neg_kernel_cuda) +REGISTER_DISPATCH(sign_stub, &sign_kernel_cuda) +REGISTER_DISPATCH(signbit_stub, &signbit_kernel_cuda) +REGISTER_DISPATCH(sgn_stub, &sgn_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnarySpecialOpsKernel.cu b/aten/src/ATen/native/cuda/UnarySpecialOpsKernel.cu index af560d8e9a5..19b0a20748d 100644 --- a/aten/src/ATen/native/cuda/UnarySpecialOpsKernel.cu +++ b/aten/src/ATen/native/cuda/UnarySpecialOpsKernel.cu @@ -378,21 +378,21 @@ void entr_kernel_cuda(TensorIteratorBase& iter) { #endif } -REGISTER_DISPATCH(exp2_stub, &exp2_kernel_cuda); -REGISTER_DISPATCH(i0_stub, &i0_kernel_cuda); -REGISTER_DISPATCH(special_i0e_stub, &i0e_kernel_cuda); -REGISTER_DISPATCH(special_i1_stub, &i1_kernel_cuda); -REGISTER_DISPATCH(special_i1e_stub, &i1e_kernel_cuda); -REGISTER_DISPATCH(sigmoid_stub, &sigmoid_kernel_cuda); -REGISTER_DISPATCH(sinc_stub, &sinc_kernel_cuda); -REGISTER_DISPATCH(logit_stub, &logit_kernel_cuda); -REGISTER_DISPATCH(erf_stub, &erf_kernel_cuda); -REGISTER_DISPATCH(erfc_stub, &erfc_kernel_cuda); -REGISTER_DISPATCH(erfinv_stub, &erfinv_kernel_cuda); -REGISTER_DISPATCH(kaiser_window_stub, &kaiser_window_kernel_cuda); -REGISTER_DISPATCH(special_entr_stub, &entr_kernel_cuda); -REGISTER_DISPATCH(special_ndtri_stub, &ndtri_kernel_cuda); -REGISTER_DISPATCH(special_log_ndtr_stub, &log_ndtr_kernel_cuda); -REGISTER_DISPATCH(special_erfcx_stub, &erfcx_kernel_cuda); +REGISTER_DISPATCH(exp2_stub, &exp2_kernel_cuda) +REGISTER_DISPATCH(i0_stub, &i0_kernel_cuda) +REGISTER_DISPATCH(special_i0e_stub, &i0e_kernel_cuda) +REGISTER_DISPATCH(special_i1_stub, &i1_kernel_cuda) +REGISTER_DISPATCH(special_i1e_stub, &i1e_kernel_cuda) +REGISTER_DISPATCH(sigmoid_stub, &sigmoid_kernel_cuda) +REGISTER_DISPATCH(sinc_stub, &sinc_kernel_cuda) +REGISTER_DISPATCH(logit_stub, &logit_kernel_cuda) +REGISTER_DISPATCH(erf_stub, &erf_kernel_cuda) +REGISTER_DISPATCH(erfc_stub, &erfc_kernel_cuda) +REGISTER_DISPATCH(erfinv_stub, &erfinv_kernel_cuda) +REGISTER_DISPATCH(kaiser_window_stub, &kaiser_window_kernel_cuda) +REGISTER_DISPATCH(special_entr_stub, &entr_kernel_cuda) +REGISTER_DISPATCH(special_ndtri_stub, &ndtri_kernel_cuda) +REGISTER_DISPATCH(special_log_ndtr_stub, &log_ndtr_kernel_cuda) +REGISTER_DISPATCH(special_erfcx_stub, &erfcx_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/UnfoldBackwardKernel.cu b/aten/src/ATen/native/cuda/UnfoldBackwardKernel.cu index 2f48d4fc014..a7ca9455977 100644 --- a/aten/src/ATen/native/cuda/UnfoldBackwardKernel.cu +++ b/aten/src/ATen/native/cuda/UnfoldBackwardKernel.cu @@ -157,6 +157,6 @@ void unfold_backward_cuda_kernel( } -REGISTER_DISPATCH(unfold_backward_stub, &unfold_backward_cuda_kernel); +REGISTER_DISPATCH(unfold_backward_stub, &unfold_backward_cuda_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/ZetaKernel.cu b/aten/src/ATen/native/cuda/ZetaKernel.cu index da536e8adbd..34aa70d1ac6 100644 --- a/aten/src/ATen/native/cuda/ZetaKernel.cu +++ b/aten/src/ATen/native/cuda/ZetaKernel.cu @@ -34,6 +34,6 @@ void zeta_kernel_cuda(TensorIteratorBase& iter) { } // namespace (anonymous) -REGISTER_DISPATCH(zeta_stub, &zeta_kernel_cuda); +REGISTER_DISPATCH(zeta_stub, &zeta_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/airy_ai.cu b/aten/src/ATen/native/cuda/airy_ai.cu index 05257c99b1b..1c42d5818cb 100644 --- a/aten/src/ATen/native/cuda/airy_ai.cu +++ b/aten/src/ATen/native/cuda/airy_ai.cu @@ -38,5 +38,5 @@ void airy_ai_kernel_cuda(TensorIteratorBase& iterator) { } // anonymous namespace -REGISTER_DISPATCH(special_airy_ai_stub, &airy_ai_kernel_cuda); +REGISTER_DISPATCH(special_airy_ai_stub, &airy_ai_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/bessel_j0.cu b/aten/src/ATen/native/cuda/bessel_j0.cu index a3d9b668e95..e39fc591007 100644 --- a/aten/src/ATen/native/cuda/bessel_j0.cu +++ b/aten/src/ATen/native/cuda/bessel_j0.cu @@ -38,5 +38,5 @@ void bessel_j0_kernel_cuda(TensorIteratorBase& iterator) { } // anonymous namespace -REGISTER_DISPATCH(special_bessel_j0_stub, &bessel_j0_kernel_cuda); +REGISTER_DISPATCH(special_bessel_j0_stub, &bessel_j0_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/bessel_j1.cu b/aten/src/ATen/native/cuda/bessel_j1.cu index 674fcadfdff..c54bb6e6ae7 100644 --- a/aten/src/ATen/native/cuda/bessel_j1.cu +++ b/aten/src/ATen/native/cuda/bessel_j1.cu @@ -38,5 +38,5 @@ void bessel_j1_kernel_cuda(TensorIteratorBase& iterator) { } // anonymous namespace -REGISTER_DISPATCH(special_bessel_j1_stub, &bessel_j1_kernel_cuda); +REGISTER_DISPATCH(special_bessel_j1_stub, &bessel_j1_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/bessel_y0.cu b/aten/src/ATen/native/cuda/bessel_y0.cu index 344ea387652..8564a9ae0b1 100644 --- a/aten/src/ATen/native/cuda/bessel_y0.cu +++ b/aten/src/ATen/native/cuda/bessel_y0.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_bessel_y0_stub, &bessel_y0_kernel_cuda); + REGISTER_DISPATCH(special_bessel_y0_stub, &bessel_y0_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/bessel_y1.cu b/aten/src/ATen/native/cuda/bessel_y1.cu index 32433a22b0b..356cdbe2302 100644 --- a/aten/src/ATen/native/cuda/bessel_y1.cu +++ b/aten/src/ATen/native/cuda/bessel_y1.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_bessel_y1_stub, &bessel_y1_kernel_cuda); + REGISTER_DISPATCH(special_bessel_y1_stub, &bessel_y1_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/chebyshev_polynomial_t.cu b/aten/src/ATen/native/cuda/chebyshev_polynomial_t.cu index a84e0c5050e..fb861b6b565 100644 --- a/aten/src/ATen/native/cuda/chebyshev_polynomial_t.cu +++ b/aten/src/ATen/native/cuda/chebyshev_polynomial_t.cu @@ -27,5 +27,5 @@ namespace at::native { } // chebyshev_polynomial_t_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(chebyshev_polynomial_t_stub, &chebyshev_polynomial_t_kernel_cuda); + REGISTER_DISPATCH(chebyshev_polynomial_t_stub, &chebyshev_polynomial_t_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/chebyshev_polynomial_u.cu b/aten/src/ATen/native/cuda/chebyshev_polynomial_u.cu index 9ec870fd130..1ca53aba217 100644 --- a/aten/src/ATen/native/cuda/chebyshev_polynomial_u.cu +++ b/aten/src/ATen/native/cuda/chebyshev_polynomial_u.cu @@ -27,5 +27,5 @@ namespace at::native { } // chebyshev_polynomial_u_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(chebyshev_polynomial_u_stub, &chebyshev_polynomial_u_kernel_cuda); + REGISTER_DISPATCH(chebyshev_polynomial_u_stub, &chebyshev_polynomial_u_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/chebyshev_polynomial_v.cu b/aten/src/ATen/native/cuda/chebyshev_polynomial_v.cu index 7f393d9d674..0dec021c1fb 100644 --- a/aten/src/ATen/native/cuda/chebyshev_polynomial_v.cu +++ b/aten/src/ATen/native/cuda/chebyshev_polynomial_v.cu @@ -27,5 +27,5 @@ namespace at::native { } // chebyshev_polynomial_v_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(chebyshev_polynomial_v_stub, &chebyshev_polynomial_v_kernel_cuda); + REGISTER_DISPATCH(chebyshev_polynomial_v_stub, &chebyshev_polynomial_v_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/chebyshev_polynomial_w.cu b/aten/src/ATen/native/cuda/chebyshev_polynomial_w.cu index 9897213ee97..1475385d386 100644 --- a/aten/src/ATen/native/cuda/chebyshev_polynomial_w.cu +++ b/aten/src/ATen/native/cuda/chebyshev_polynomial_w.cu @@ -27,5 +27,5 @@ namespace at::native { } // chebyshev_polynomial_w_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(chebyshev_polynomial_w_stub, &chebyshev_polynomial_w_kernel_cuda); + REGISTER_DISPATCH(chebyshev_polynomial_w_stub, &chebyshev_polynomial_w_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/group_norm_kernel.cu b/aten/src/ATen/native/cuda/group_norm_kernel.cu index 5bb81ae70f1..97ab0c2d934 100644 --- a/aten/src/ATen/native/cuda/group_norm_kernel.cu +++ b/aten/src/ATen/native/cuda/group_norm_kernel.cu @@ -990,7 +990,7 @@ void GroupNormBackwardKernelImpl( } // namespace -REGISTER_DISPATCH(GroupNormKernel, &GroupNormKernelImpl); -REGISTER_DISPATCH(GroupNormBackwardKernel, &GroupNormBackwardKernelImpl); +REGISTER_DISPATCH(GroupNormKernel, &GroupNormKernelImpl) +REGISTER_DISPATCH(GroupNormBackwardKernel, &GroupNormBackwardKernelImpl) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/hermite_polynomial_h.cu b/aten/src/ATen/native/cuda/hermite_polynomial_h.cu index d581e38bbef..1d1ded792c2 100644 --- a/aten/src/ATen/native/cuda/hermite_polynomial_h.cu +++ b/aten/src/ATen/native/cuda/hermite_polynomial_h.cu @@ -27,5 +27,5 @@ namespace at::native { } // hermite_polynomial_h_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(hermite_polynomial_h_stub, &hermite_polynomial_h_kernel_cuda); + REGISTER_DISPATCH(hermite_polynomial_h_stub, &hermite_polynomial_h_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/hermite_polynomial_he.cu b/aten/src/ATen/native/cuda/hermite_polynomial_he.cu index b5b1891b80c..811c035b6b5 100644 --- a/aten/src/ATen/native/cuda/hermite_polynomial_he.cu +++ b/aten/src/ATen/native/cuda/hermite_polynomial_he.cu @@ -27,5 +27,5 @@ namespace at::native { } // hermite_polynomial_he_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(hermite_polynomial_he_stub, &hermite_polynomial_he_kernel_cuda); + REGISTER_DISPATCH(hermite_polynomial_he_stub, &hermite_polynomial_he_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/laguerre_polynomial_l.cu b/aten/src/ATen/native/cuda/laguerre_polynomial_l.cu index 0490fc97cc5..73232d4e640 100644 --- a/aten/src/ATen/native/cuda/laguerre_polynomial_l.cu +++ b/aten/src/ATen/native/cuda/laguerre_polynomial_l.cu @@ -27,5 +27,5 @@ namespace at::native { } // laguerre_polynomial_l_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(laguerre_polynomial_l_stub, &laguerre_polynomial_l_kernel_cuda); + REGISTER_DISPATCH(laguerre_polynomial_l_stub, &laguerre_polynomial_l_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/layer_norm_kernel.cu b/aten/src/ATen/native/cuda/layer_norm_kernel.cu index 8c9a5d47b45..b8f41ba5677 100644 --- a/aten/src/ATen/native/cuda/layer_norm_kernel.cu +++ b/aten/src/ATen/native/cuda/layer_norm_kernel.cu @@ -1459,7 +1459,7 @@ std::tuple layer_norm_backward_cuda( return std::make_tuple(std::move(dX), std::move(dgamma), std::move(dbeta)); } -REGISTER_DISPATCH(LayerNormKernel, &LayerNormKernelImpl); -REGISTER_DISPATCH(LayerNormBackwardKernel, &LayerNormBackwardKernelImpl); +REGISTER_DISPATCH(LayerNormKernel, &LayerNormKernelImpl) +REGISTER_DISPATCH(LayerNormBackwardKernel, &LayerNormBackwardKernelImpl) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/legendre_polynomial_p.cu b/aten/src/ATen/native/cuda/legendre_polynomial_p.cu index 9f5efc9b451..24b4f1c4ebc 100644 --- a/aten/src/ATen/native/cuda/legendre_polynomial_p.cu +++ b/aten/src/ATen/native/cuda/legendre_polynomial_p.cu @@ -27,5 +27,5 @@ namespace at::native { } // legendre_polynomial_p_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(legendre_polynomial_p_stub, &legendre_polynomial_p_kernel_cuda); + REGISTER_DISPATCH(legendre_polynomial_p_stub, &legendre_polynomial_p_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/modified_bessel_i0.cu b/aten/src/ATen/native/cuda/modified_bessel_i0.cu index 5d5e60c132c..4d3197cdce9 100644 --- a/aten/src/ATen/native/cuda/modified_bessel_i0.cu +++ b/aten/src/ATen/native/cuda/modified_bessel_i0.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_modified_bessel_i0_stub, &modified_bessel_i0_kernel_cuda); + REGISTER_DISPATCH(special_modified_bessel_i0_stub, &modified_bessel_i0_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/modified_bessel_i1.cu b/aten/src/ATen/native/cuda/modified_bessel_i1.cu index 4576ce07042..ff104f54ce7 100644 --- a/aten/src/ATen/native/cuda/modified_bessel_i1.cu +++ b/aten/src/ATen/native/cuda/modified_bessel_i1.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_modified_bessel_i1_stub, &modified_bessel_i1_kernel_cuda); + REGISTER_DISPATCH(special_modified_bessel_i1_stub, &modified_bessel_i1_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/modified_bessel_k0.cu b/aten/src/ATen/native/cuda/modified_bessel_k0.cu index 17de0d94a69..68299e8f9f3 100644 --- a/aten/src/ATen/native/cuda/modified_bessel_k0.cu +++ b/aten/src/ATen/native/cuda/modified_bessel_k0.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_modified_bessel_k0_stub, &modified_bessel_k0_kernel_cuda); + REGISTER_DISPATCH(special_modified_bessel_k0_stub, &modified_bessel_k0_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/modified_bessel_k1.cu b/aten/src/ATen/native/cuda/modified_bessel_k1.cu index a858ad52af6..f7423359c46 100644 --- a/aten/src/ATen/native/cuda/modified_bessel_k1.cu +++ b/aten/src/ATen/native/cuda/modified_bessel_k1.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_modified_bessel_k1_stub, &modified_bessel_k1_kernel_cuda); + REGISTER_DISPATCH(special_modified_bessel_k1_stub, &modified_bessel_k1_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/scaled_modified_bessel_k0.cu b/aten/src/ATen/native/cuda/scaled_modified_bessel_k0.cu index 880b6b54c18..120666b87b0 100644 --- a/aten/src/ATen/native/cuda/scaled_modified_bessel_k0.cu +++ b/aten/src/ATen/native/cuda/scaled_modified_bessel_k0.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_scaled_modified_bessel_k0_stub, &scaled_modified_bessel_k0_kernel_cuda); + REGISTER_DISPATCH(special_scaled_modified_bessel_k0_stub, &scaled_modified_bessel_k0_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/scaled_modified_bessel_k1.cu b/aten/src/ATen/native/cuda/scaled_modified_bessel_k1.cu index 7e5c771dc80..2114585e4ac 100644 --- a/aten/src/ATen/native/cuda/scaled_modified_bessel_k1.cu +++ b/aten/src/ATen/native/cuda/scaled_modified_bessel_k1.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_scaled_modified_bessel_k1_stub, &scaled_modified_bessel_k1_kernel_cuda); + REGISTER_DISPATCH(special_scaled_modified_bessel_k1_stub, &scaled_modified_bessel_k1_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_t.cu b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_t.cu index e08081495ec..fd917b283d6 100644 --- a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_t.cu +++ b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_t.cu @@ -27,5 +27,5 @@ namespace at::native { } // shifted_chebyshev_polynomial_t_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(shifted_chebyshev_polynomial_t_stub, &shifted_chebyshev_polynomial_t_kernel_cuda); + REGISTER_DISPATCH(shifted_chebyshev_polynomial_t_stub, &shifted_chebyshev_polynomial_t_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_u.cu b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_u.cu index 12fe938334a..49f3fac5a02 100644 --- a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_u.cu +++ b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_u.cu @@ -27,5 +27,5 @@ namespace at::native { } // shifted_chebyshev_polynomial_u_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(shifted_chebyshev_polynomial_u_stub, &shifted_chebyshev_polynomial_u_kernel_cuda); + REGISTER_DISPATCH(shifted_chebyshev_polynomial_u_stub, &shifted_chebyshev_polynomial_u_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_v.cu b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_v.cu index 19db5a5ed53..870ce5bc811 100644 --- a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_v.cu +++ b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_v.cu @@ -28,5 +28,5 @@ void shifted_chebyshev_polynomial_v_kernel_cuda(TensorIteratorBase& iterator) { } // namespace (anonymous) -REGISTER_DISPATCH(shifted_chebyshev_polynomial_v_stub, &shifted_chebyshev_polynomial_v_kernel_cuda); +REGISTER_DISPATCH(shifted_chebyshev_polynomial_v_stub, &shifted_chebyshev_polynomial_v_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_w.cu b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_w.cu index d53b026947a..acdfea904ad 100644 --- a/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_w.cu +++ b/aten/src/ATen/native/cuda/shifted_chebyshev_polynomial_w.cu @@ -27,5 +27,5 @@ namespace at::native { } // shifted_chebyshev_polynomial_w_kernel_cuda } // namespace (anonymous) - REGISTER_DISPATCH(shifted_chebyshev_polynomial_w_stub, &shifted_chebyshev_polynomial_w_kernel_cuda); + REGISTER_DISPATCH(shifted_chebyshev_polynomial_w_stub, &shifted_chebyshev_polynomial_w_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/cuda/spherical_bessel_j0.cu b/aten/src/ATen/native/cuda/spherical_bessel_j0.cu index 14234b27e54..dc225505dc7 100644 --- a/aten/src/ATen/native/cuda/spherical_bessel_j0.cu +++ b/aten/src/ATen/native/cuda/spherical_bessel_j0.cu @@ -37,5 +37,5 @@ namespace at::native { } } - REGISTER_DISPATCH(special_spherical_bessel_j0_stub, &spherical_bessel_j0_kernel_cuda); + REGISTER_DISPATCH(special_spherical_bessel_j0_stub, &spherical_bessel_j0_kernel_cuda) } // namespace at::native diff --git a/aten/src/ATen/native/metal/MetalGuardImpl.cpp b/aten/src/ATen/native/metal/MetalGuardImpl.cpp index faf496a6095..9dc41c1d2df 100644 --- a/aten/src/ATen/native/metal/MetalGuardImpl.cpp +++ b/aten/src/ATen/native/metal/MetalGuardImpl.cpp @@ -58,7 +58,7 @@ struct MetalGuardImpl final : public c10::impl::DeviceGuardImplInterface { noexcept override {} }; -C10_REGISTER_GUARD_IMPL(Metal, MetalGuardImpl); +C10_REGISTER_GUARD_IMPL(Metal, MetalGuardImpl) } // namespace detail } // namespace at diff --git a/aten/src/ATen/native/mps/operations/BinaryKernel.mm b/aten/src/ATen/native/mps/operations/BinaryKernel.mm index 89a171bbb59..67292674f7d 100644 --- a/aten/src/ATen/native/mps/operations/BinaryKernel.mm +++ b/aten/src/ATen/native/mps/operations/BinaryKernel.mm @@ -111,10 +111,10 @@ static void nextafter_mps_kernel(TensorIteratorBase& iter) { mps::binary_mps_impl(iter, "nextafter_kernel"); } -REGISTER_DISPATCH(fmax_stub, &fmax_mps_kernel); -REGISTER_DISPATCH(fmin_stub, &fmin_mps_kernel); -REGISTER_DISPATCH(copysign_stub, ©sign_mps_kernel); -REGISTER_DISPATCH(nextafter_stub, &nextafter_mps_kernel); +REGISTER_DISPATCH(fmax_stub, &fmax_mps_kernel) +REGISTER_DISPATCH(fmin_stub, &fmin_mps_kernel) +REGISTER_DISPATCH(copysign_stub, ©sign_mps_kernel) +REGISTER_DISPATCH(nextafter_stub, &nextafter_mps_kernel) Tensor& polar_out_mps(const Tensor& abs, const Tensor& angle, Tensor& output) { auto new_size = at::infer_size(abs.sizes(), angle.sizes()); diff --git a/aten/src/ATen/native/mps/operations/CrossKernel.mm b/aten/src/ATen/native/mps/operations/CrossKernel.mm index fbdfe38dde3..9f19824599d 100644 --- a/aten/src/ATen/native/mps/operations/CrossKernel.mm +++ b/aten/src/ATen/native/mps/operations/CrossKernel.mm @@ -61,5 +61,5 @@ void cross_mps_impl(const Tensor& out, const Tensor& input, const Tensor& other, } } // anonymous namespace -REGISTER_DISPATCH(cross_stub, &cross_mps_impl); +REGISTER_DISPATCH(cross_stub, &cross_mps_impl) } // namespace at::native diff --git a/aten/src/ATen/native/mps/operations/HistogramKernel.mm b/aten/src/ATen/native/mps/operations/HistogramKernel.mm index 55cdaaab4a7..561712b3784 100644 --- a/aten/src/ATen/native/mps/operations/HistogramKernel.mm +++ b/aten/src/ATen/native/mps/operations/HistogramKernel.mm @@ -238,7 +238,7 @@ static void histogram_select_outer_bin_edges_kernel(const Tensor& input, } } -REGISTER_DISPATCH(histogramdd_stub, &histogramdd_kernel); -REGISTER_DISPATCH(histogramdd_linear_stub, &histogramdd_linear_kernel); -REGISTER_DISPATCH(histogram_select_outer_bin_edges_stub, &histogram_select_outer_bin_edges_kernel); +REGISTER_DISPATCH(histogramdd_stub, &histogramdd_kernel) +REGISTER_DISPATCH(histogramdd_linear_stub, &histogramdd_linear_kernel) +REGISTER_DISPATCH(histogram_select_outer_bin_edges_stub, &histogram_select_outer_bin_edges_kernel) } // namespace at::native diff --git a/aten/src/ATen/native/mps/operations/Indexing.mm b/aten/src/ATen/native/mps/operations/Indexing.mm index a13e660b9c8..7b84d6bdb4d 100644 --- a/aten/src/ATen/native/mps/operations/Indexing.mm +++ b/aten/src/ATen/native/mps/operations/Indexing.mm @@ -957,6 +957,6 @@ Tensor& index_fill_mps_(Tensor& self, int64_t dim, const Tensor& index, const Sc return self.index_fill_(dim, index, mps::wrapped_scalar_tensor_mps(source, self.device())); } -REGISTER_DISPATCH(index_stub, &mps::index_kernel_mps); -REGISTER_DISPATCH(index_put_stub, &mps::index_put_kernel_mps); +REGISTER_DISPATCH(index_stub, &mps::index_kernel_mps) +REGISTER_DISPATCH(index_put_stub, &mps::index_put_kernel_mps) } // namespace at::native diff --git a/aten/src/ATen/native/mps/operations/SpecialOps.mm b/aten/src/ATen/native/mps/operations/SpecialOps.mm index 55f99c4e80e..6b0e3bb7eee 100644 --- a/aten/src/ATen/native/mps/operations/SpecialOps.mm +++ b/aten/src/ATen/native/mps/operations/SpecialOps.mm @@ -42,5 +42,5 @@ static void i0_kernel_mps(TensorIteratorBase& iter) { } } -REGISTER_DISPATCH(i0_stub, &i0_kernel_mps); +REGISTER_DISPATCH(i0_stub, &i0_kernel_mps) } // namespace at::native diff --git a/aten/src/ATen/native/mps/operations/TensorCompare.mm b/aten/src/ATen/native/mps/operations/TensorCompare.mm index 78c91624811..7a72568a705 100644 --- a/aten/src/ATen/native/mps/operations/TensorCompare.mm +++ b/aten/src/ATen/native/mps/operations/TensorCompare.mm @@ -570,8 +570,8 @@ static void isposinf_kernel_mps(TensorIteratorBase& iter) { mps::is_posneginf_helper(iter, false); } -REGISTER_DISPATCH(where_kernel, &where_kernel_mps); -REGISTER_DISPATCH(isneginf_stub, &isneginf_kernel_mps); -REGISTER_DISPATCH(isposinf_stub, &isposinf_kernel_mps); +REGISTER_DISPATCH(where_kernel, &where_kernel_mps) +REGISTER_DISPATCH(isneginf_stub, &isneginf_kernel_mps) +REGISTER_DISPATCH(isposinf_stub, &isposinf_kernel_mps) } // namespace at::native diff --git a/aten/src/ATen/native/quantized/cpu/kernels/QuantizedOpKernels.cpp b/aten/src/ATen/native/quantized/cpu/kernels/QuantizedOpKernels.cpp index c29a7a55b9e..e115fb5c06f 100644 --- a/aten/src/ATen/native/quantized/cpu/kernels/QuantizedOpKernels.cpp +++ b/aten/src/ATen/native/quantized/cpu/kernels/QuantizedOpKernels.cpp @@ -4279,8 +4279,8 @@ ALSO_REGISTER_AVX512_DISPATCH(dequantize_tensor_per_channel_float_qparams_stub, &dequantize_tensor_per_channel_float_qparams_cpu); ALSO_REGISTER_AVX512_DISPATCH(fake_quant_per_channel_cachemask_stub, &fake_quant_per_channel_cachemask_cpu); -ALSO_REGISTER_AVX512_DISPATCH(qavg_pool2d_nhwc_stub, &qavg_pool2d_nhwc_kernel); -ALSO_REGISTER_AVX512_DISPATCH(qavg_pool3d_nhwc_stub, &qavg_pool3d_nhwc_kernel); +ALSO_REGISTER_AVX512_DISPATCH(qavg_pool2d_nhwc_stub, &qavg_pool2d_nhwc_kernel) +ALSO_REGISTER_AVX512_DISPATCH(qavg_pool3d_nhwc_stub, &qavg_pool3d_nhwc_kernel) #endif // CPU_CAPABILITY_AVX512 && _WIN32 // The kernels below are dispatched to AVX2 because they don't perform as well diff --git a/aten/src/ATen/native/vulkan/VulkanGuardImpl.cpp b/aten/src/ATen/native/vulkan/VulkanGuardImpl.cpp index 6432adf1da5..0b0ee9d5901 100644 --- a/aten/src/ATen/native/vulkan/VulkanGuardImpl.cpp +++ b/aten/src/ATen/native/vulkan/VulkanGuardImpl.cpp @@ -77,7 +77,7 @@ struct VulkanGuardImpl final : public c10::impl::DeviceGuardImplInterface { } // namespace -C10_REGISTER_GUARD_IMPL(Vulkan, VulkanGuardImpl); +C10_REGISTER_GUARD_IMPL(Vulkan, VulkanGuardImpl) } // namespace detail } // namespace at